© 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. 43216
    Prev
    Next
    INDEX
    Explanations

    end-to-end

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

    lists patterns

    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
    级别
    0.43
    ␊
    0.42
    级别的
    0.41
     Aucun
    0.40
    等级
    0.40
     <?=
    0.40
    జ్
    0.39
     współprac
    0.39
    ไ
    0.39
    ∗</
    0.38
    POSITIVE LOGITS
    از
    0.47
     از
    0.43
    saya
    0.41
     Christen
    0.41
    さすが
    0.41
     Hunters
    0.39
    ulls
    0.39
    ಿಸುತ್ತಾರೆ
    0.39
     sandals
    0.38
     created
    0.38
    Activations Density 0.001%

    No Known Activations