© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    math notation and symbols

    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
    ួក
    0.50
    ាតុ
    0.48
     élytres
    0.48
    ្នែក
    0.48
    မ်း
    0.47
    ार्टमेंट
    0.47
    <unused973>
    0.47
    <unused706>
    0.47
    ូង
    0.46
    ម្លៃ
    0.46
    POSITIVE LOGITS
    k
    0.61
    n
    0.59
    K
    0.57
     n
    0.57
    1
    0.57
     p
    0.55
    S
    0.54
    0
    0.52
      
    0.52
    z
    0.52
    Activations Density 0.027%

    No Known Activations