© 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. 67114
    Prev
    Next
    INDEX
    Explanations

    closing actions, window events

    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
    geſ
    -2.30
     ofere
    -1.97
     encontram
    -1.77
     mantém
    -1.73
     löyty
    -1.70
     réussite
    -1.66
    鐃
    -1.66
     necessárias
    -1.63
     manten
    -1.61
     pandémie
    -1.61
    POSITIVE LOGITS
     is
    1.70
    -
    1.65
    CloseOperation
    1.56
     inexorable
    1.48
    .
    1.46
    WindowConstants
    1.45
     Stepping
    1.41
     Previously
    1.40
    ,”
    1.38
    泪
    1.38
    Activations Density 0.002%

    No Known Activations