© 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. 68024
    Prev
    Next
    INDEX
    Explanations

    direct serve

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

    file attributes and descriptors

    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
    adaş
    0.50
    เหล่านี้
    0.50
     jurisdictions
    0.48
     преобразова
    0.47
    കൾ
    0.46
     bầu
    0.45
    一个个
    0.45
    ıştı
    0.45
    越来越多
    0.44
    Ẫ
    0.44
    POSITIVE LOGITS
    FileInfo
    0.55
    File
    0.55
     for
    0.50
     時
    0.48
    FILE
    0.47
    要
    0.47
     Existe
    0.47
     at
    0.46
     formant
    0.46
    file
    0.45
    Activations Density 0.000%

    No Known Activations