© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6660
    Prev
    Next
    INDEX
    Explanations

    Rollup JavaScript exports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    錆
    0.52
    電流
    0.48
     liegen
    0.48
    擔任
    0.48
     Règles
    0.46
    歷史
    0.46
    يي
    0.45
     автомобі
    0.44
     પાણી
    0.44
     історії
    0.43
    POSITIVE LOGITS
    exports
    0.57
    cjs
    0.55
    Object
    0.53
    /******/
    0.53
     exports
    0.51
    /**
    0.50
     /**
    0.49
    esm
    0.49
    export
    0.49
    var
    0.48
    Activations Density 0.019%

    No Known Activations