© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186731
    Prev
    Next
    INDEX
    Explanations

    paths and identifiers

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

    client APIs and code imports

    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
    de
    0.56
    ogran
    0.53
    <0x80>
    0.47
     Porque
    0.47
     Chernobyl
    0.45
     Antes
    0.44
    esson
    0.44
    多家
    0.43
    renc
    0.42
    ं
    0.42
    POSITIVE LOGITS
    ™
    0.46
    ®,
    0.45
    網站
    0.45
     앱
    0.43
     intranet
    0.43
     cliente
    0.43
    ™,
    0.42
    鐐
    0.42
     nền
    0.42
    ®
    0.42
    Activations Density 0.042%

    No Known Activations