© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132123
    Prev
    Next
    INDEX
    Explanations

    return information

    np_acts-logits-general · gemini-2.5-flash-lite

    official status or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivasena
    0.50
    revolution
    0.47
     "&#
    0.46
    ohex
    0.45
    어나
    0.44
    ֗
    0.44
    mouseover
    0.43
    어로
    0.43
     قرمز
    0.42
    밂
    0.42
    POSITIVE LOGITS
     in
    0.59
    ção
    0.57
     Customs
    0.56
    prese
    0.54
     at
    0.52
    şi
    0.52
    ším
    0.50
     prosecuting
    0.50
     parach
    0.49
    á
    0.49
    Activations Density 0.001%

    No Known Activations