© 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. 37313
    Prev
    Next
    INDEX
    Explanations

    checking facts

    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
     cosmopolitan
    0.48
     country
    0.46
     ഹിന്ദ
    0.45
    ↵
    0.45
     Hartley
    0.45
     Country
    0.44
     day
    0.43
     thể
    0.43
    ,.
    0.43
     zeta
    0.43
    POSITIVE LOGITS
    IMPORTANT
    0.46
    人們
    0.46
    議員
    0.45
    늪
    0.45
    計画
    0.45
    وہ
    0.45
     STILL
    0.45
    ｏ
    0.45
    AutoHide
    0.44
    ਊ
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.