© 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. 151215
    Prev
    Next
    INDEX
    Explanations

    typically working

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

    general descriptions and specifics

    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
    लाब
    0.61
    ENCY
    0.49
     교회
    0.48
    곰
    0.47
    ის
    0.46
    치
    0.46
    PhCH
    0.46
     식품
    0.45
    ᆫ
    0.45
     بچے
    0.44
    POSITIVE LOGITS
     Town
    0.45
     Expo
    0.44
     млн
    0.43
     Gallup
    0.43
     incurs
    0.43
    BZ
    0.43
     deiner
    0.42
     Kho
    0.42
     দায়িত্বে
    0.42
     çoğu
    0.42
    Activations Density 0.000%

    No Known Activations