© 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. 56896
    Prev
    Next
    INDEX
    Explanations

    publications

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

    hazard mapping

    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
     (
    0.56
     Tail
    0.56
    G
    0.53
     Quality
    0.52
    at
    0.51
    c
    0.51
     Direct
    0.50
     Press
    0.50
     Final
    0.50
     Load
    0.50
    POSITIVE LOGITS
    ⱨ
    0.54
    庿
    0.54
    étude
    0.54
     LOTRAchievement
    0.53
     adhipp
    0.53
    <unused71>
    0.52
    !।
    0.52
     ScriptInterface
    0.51
     നമഃ
    0.50
     депозиттик
    0.50
    Activations Density 0.000%

    No Known Activations