© 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. 184021
    Prev
    Next
    INDEX
    Explanations

    this site/website

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

    list item formatting

    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
     protectors
    0.49
    𝓵
    0.48
    ಳಿಗೆ
    0.48
     ectopic
    0.47
     દરેક
    0.47
     spindles
    0.47
     comedians
    0.47
     भया
    0.47
     elastomers
    0.46
     মনোরম
    0.46
    POSITIVE LOGITS
    이나
    0.50
    적
    0.49
    ์
    0.49
     Ember
    0.48
    ்
    0.47
    전히
    0.46
     cán
    0.45
    보
    0.45
    ched
    0.43
     verw
    0.43
    Activations Density 0.000%

    No Known Activations