© 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. 34-GEMMASCOPE-RES-131K
    7. 56974
    Prev
    Next
    INDEX
    Explanations

    web links and urls

    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_34/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
    ,
    -1.07
     the
    -1.07
    除此
    -0.99
    $("#
    -0.94
    -------------</
    -0.93
     autre
    -0.92
    landais
    -0.91
    ?
    -0.91
    atan
    -0.90
     abgerufen
    -0.90
    POSITIVE LOGITS
     https
    1.78
    https
    1.73
     http
    1.63
    http
    1.60
    LINK
    1.23
     ссылка
    1.09
     ссылке
    1.01
    liegen
    1.00
    mitglied
    1.00
     LINK
    0.99
    Activations Density 0.089%

    No Known Activations