© 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. 24237
    Prev
    Next
    INDEX
    Explanations

    simplify, single, keep, lowest, virus

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

    character descriptions and 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
     গল্প
    0.51
     రాజకీయ
    0.45
     设计
    0.44
     🌱
    0.44
    🕌
    0.44
     politique
    0.43
    监管
    0.43
    基层
    0.43
    🌱
    0.43
    美丽
    0.42
    POSITIVE LOGITS
     مذکور
    0.52
     tersebut
    0.48
    if
    0.46
     protruding
    0.46
     evade
    0.45
    ，
    0.45
     refrained
    0.45
    iff
    0.45
     thwart
    0.44
     offres
    0.44
    Activations Density 0.000%

    No Known Activations