© 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. 10-GEMMASCOPE-RES-131K
    7. 67960
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers for ranking

    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
     rempliss
    -1.72
    aéroport
    -1.72
     excelentes
    -1.70
     aguj
    -1.63
     sportifs
    -1.62
     tirantes
    -1.59
     véritables
    -1.59
     récentes
    -1.59
     cintas
    -1.59
     cremallera
    -1.59
    POSITIVE LOGITS
     in
    3.11
     on
    2.09
    //
    1.91
    >
    1.89
    \
    1.88
    for
    1.78
     then
    1.76
     instead
    1.73
     than
    1.72
    ve
    1.71
    Activations Density 0.018%

    No Known Activations