© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139109
    Prev
    Next
    INDEX
    Explanations

    language, culture, traditions, game

    np_acts-logits-general · gemini-2.5-flash-lite

    betting and buying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    特定
    0.46
    幾乎
    0.45
    <unused1003>
    0.45
     anciennes
    0.43
     naciones
    0.43
    лок
    0.43
    込
    0.42
    🚋
    0.42
     entrambe
    0.42
    阱
    0.42
    POSITIVE LOGITS
    Sant
    0.57
    Dias
    0.50
    ETTE
    0.49
    etype
    0.48
    S
    0.47
     Sant
    0.46
    Buzz
    0.46
    es
    0.46
    Level
    0.46
    Buk
    0.46
    Activations Density 0.000%

    No Known Activations