© 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. 22-GEMMASCOPE-RES-131K
    7. 33058
    Prev
    Next
    INDEX
    Explanations

    cross product

    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_22/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
    vacation
    -0.95
     recoger
    -0.95
     çiz
    -0.89
    tactez
    -0.86
    toprule
    -0.85
     officiels
    -0.84
     promociones
    -0.84
     rebajas
    -0.84
     naviguant
    -0.83
    SEASON
    -0.82
    POSITIVE LOGITS
     Pliny
    0.87
     should
    0.77
    מק
    0.77
    को
    0.73
     選択
    0.71
    執筆
    0.71
    di
    0.71
    游戏
    0.71
     interrup
    0.71
     aimed
    0.70
    Activations Density 0.009%

    No Known Activations