© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24498
    Prev
    Next
    INDEX
    Explanations

    temperature range (-60°C to +200°C / -76°F to +392°F"- "Average is -62°C (-80°F), but can range from 20°C (68°F"- "coordinates>-122.0822035425683,37.422"- "state (-60dBm to -70dBm: Good"- "warm cryogenic temperatures (-42.1°C)."- "The robot's senses. These gather data about the environment and the robot's own state."- "Temperatures can plummet to -40°F (-40°C) or lower"The neuron activates for temperature ranges, coordinates (often with negative values), and dBm ranges/values. The presence of parentheses and hyphens around these numbers is common. The `TOP_POSITIVE_LOGITS` also contain symbolic representations of ranges and negative numbers.focus on negative numbers and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialties
    0.48
     erhöht
    0.48
     aumenta
    0.46
     повы
    0.43
     erhöhen
    0.43
    ixels
    0.42
    提高
    0.42
     বৃদ্ধির
    0.42
    Increasing
    0.41
     specialty
    0.41
    POSITIVE LOGITS
     (-)
    0.49
     Bab
    0.45
    Bab
    0.44
    ">-
    0.44
     (-
    0.43
     Baba
    0.43
     Hugo
    0.43
    (-)
    0.43
     (−
    0.42
    }=-
    0.41
    Activations Density 0.005%

    No Known Activations