© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68475
    Prev
    Next
    INDEX
    Explanations

    exports and declarations with `__esModule`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ൅
    -1.75
    deauna
    -1.60
    橚
    -1.48
     fährt
    -1.48
     barata
    -1.48
     defekt
    -1.46
     citada
    -1.45
    יפול
    -1.45
     cadeira
    -1.45
     suffit
    -1.44
    POSITIVE LOGITS
     of
    2.45
     for
    1.85
     at
    1.72
    u
    1.66
    d
    1.63
    !
    1.58
     -
    1.49
     on
    1.49
    He
    1.49
     from
    1.45
    Activations Density 0.003%

    No Known Activations