© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 22000
    Prev
    Next
    INDEX
    Explanations

    Infrared thermometers

    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
     unintentional
    0.42
     meant
    0.41
    ሑ
    0.40
     foundations
    0.40
    []
    0.39
     Downtown
    0.39
    rna
    0.39
    [$
    0.39
    uyết
    0.38
    ían
    0.38
    POSITIVE LOGITS
     पद्ध
    0.50
     sonde
    0.47
     metodologia
    0.46
     lavage
    0.46
     propane
    0.46
     स्वचालित
    0.46
     системи
    0.44
     thermocou
    0.44
     técnicas
    0.44
     methionine
    0.44
    Activations Density 0.009%

    No Known Activations