© 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. 191338
    Prev
    Next
    INDEX
    Explanations

    exceptions and authorizations

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

    labels, jump points, or lists

    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
     Helmet
    0.49
    _
    0.47
     isothermal
    0.46
     •
    0.46
    MB
    0.46
     劉
    0.46
    ),"
    0.45
     ウィ
    0.45
     khởi
    0.44
     Mt
    0.44
    POSITIVE LOGITS
    ían
    0.55
    ores
    0.54
    ada
    0.53
    했고
    0.52
    ifax
    0.50
    然后
    0.49
    adri
    0.49
    ale
    0.48
    ceans
    0.48
    邮件
    0.47
    Activations Density 0.002%

    No Known Activations