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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5442
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis single quote

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

    code delimiters and comments

    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
    OSED
    0.31
    ANE
    0.30
    基督
    0.30
    隂
    0.30
    DUC
    0.30
    WOOD
    0.30
     الحسن
    0.29
    гон
    0.29
    CLUS
    0.29
    بوب
    0.29
    POSITIVE LOGITS
    desIP
    0.30
    ↵
    0.27
    chomp
    0.25
    navigationItem
    0.25
     it
    0.25
    oretically
    0.25
    ingly
    0.24
     It
    0.24
    ually
    0.24
    ouncing
    0.24
    Activations Density 0.000%

    No Known Activations