© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 62187
    Prev
    Next
    INDEX
    Explanations

    dart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    굴
    0.41
    ahankan
    0.41
    ロール
    0.38
    MakeRange
    0.37
    帆
    0.37
    featureType
    0.36
    ุท
    0.36
    盂
    0.36
    HING
    0.36
    BIR
    0.36
    POSITIVE LOGITS
     darts
    1.54
     dart
    1.45
     Dart
    1.31
    dart
    1.23
    Dart
    1.20
     dard
    0.89
    鏢
    0.84
     Dard
    0.77
     Dartmouth
    0.73
     DAR
    0.73
    Activations Density 0.001%

    No Known Activations