© 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. 141430
    Prev
    Next
    INDEX
    Explanations

    food, personnel accompanying, performance year, new learning

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

    catchy hook, risk of default

    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
     llamas
    0.55
     cartas
    0.53
     raises
    0.50
     letters
    0.49
     logo
    0.48
     checked
    0.48
    :
    0.48
     y
    0.47
     ll
    0.47
     nome
    0.47
    POSITIVE LOGITS
     डोंग
    0.49
     रेंज
    0.49
    阱
    0.48
    𝐚
    0.48
    graduate
    0.48
    istiche
    0.46
     ईवी
    0.46
    インストール
    0.46
    시키
    0.46
    verk
    0.45
    Activations Density 0.000%

    No Known Activations