© 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. 177241
    Prev
    Next
    INDEX
    Explanations

    help, want, solution, answer

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

    program code or foreign names

    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
     winemaker
    0.55
     Tief
    0.50
    ona
    0.50
     renormalized
    0.49
     wineries
    0.46
    实行
    0.46
     c
    0.44
    手里
    0.44
     deno
    0.44
     underpinning
    0.44
    POSITIVE LOGITS
     arah
    0.50
     проще
    0.50
    情報
    0.45
    ARR
    0.45
    ارہ
    0.45
    nonsense
    0.44
    PRESS
    0.44
    向け
    0.44
    読
    0.44
    リス
    0.42
    Activations Density 0.001%

    No Known Activations