© 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. 141424
    Prev
    Next
    INDEX
    Explanations

    allegation, alleged, drug, lender

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

    descriptions, styles, features

    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
    Negative Logits
    新能源
    0.46
     গাড়ীতে
    0.45
     моде
    0.44
    动画
    0.43
     முடி
    0.43
     మొత్తం
    0.43
     முடிய
    0.42
    结
    0.42
     задачи
    0.41
    清晰
    0.41
    POSITIVE LOGITS
     sám
    0.49
     stores
    0.48
     allegation
    0.48
     れる
    0.47
     bullshit
    0.46
     affliction
    0.46
     boli
    0.45
     allegations
    0.44
     offending
    0.44
     alleged
    0.44
    Activations Density 0.001%

    No Known Activations