© 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. 232379
    Prev
    Next
    INDEX
    Explanations

    may join

    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
    藍
    0.52
    氏
    0.51
     Verbindung
    0.50
    酢
    0.49
    バージョン
    0.49
    欽
    0.47
    接続
    0.46
    ◹
    0.46
    発明
    0.46
     vorgesch
    0.46
    POSITIVE LOGITS
     Expenditure
    0.46
     Apostolic
    0.45
     پای
    0.45
     season
    0.44
     expenditure
    0.43
    il
    0.43
     Sheep
    0.43
     ویس
    0.43
    -(
    0.42
     പറ്റ
    0.42
    Activations Density 0.000%

    No Known Activations