© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93038
    Prev
    Next
    INDEX
    Explanations

    function code snippets

    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
     while
    -1.80
     WHILE
    -1.45
    While
    -1.36
    WHILE
    -1.36
    while
    -1.34
     mientras
    -1.34
     mentre
    -1.20
     While
    -1.13
     enquanto
    -1.13
     ενώ
    -1.09
    POSITIVE LOGITS
    var
    1.97
    _,
    1.62
     var
    1.41
     _,
    1.35
    err
    1.16
    if
    1.16
    //
    1.08
     fmt
    1.06
    fmt
    1.06
     err
    1.03
    Activations Density 0.013%

    No Known Activations