© 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. 146303
    Prev
    Next
    INDEX
    Explanations

    goat milk, mobile applications, Lyft, science

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

    ONNX Runtime, despair, Isla, pre, code, and

    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
    frameNStart
    0.50
    오늘
    0.45
    isAuthenticated
    0.44
    ጿ
    0.44
    一百
    0.43
    参考文献
    0.43
    ैया
    0.41
    iszt
    0.41
    全世界
    0.41
     marin
    0.40
    POSITIVE LOGITS
    ،
    0.62
     الحياة
    0.51
    ’
    0.46
     ಮತ್ತು
    0.44
     প্রকৃতি
    0.44
     និង
    0.44
    ，《
    0.42
     भटक
    0.42
    hernalia
    0.42
    ؛
    0.42
    Activations Density 0.000%

    No Known Activations