© 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. 52065
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    legal and technical terms

    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
    ⏎
    0.46
    CURSOR
    0.43
    oL
    0.42
    REPORT
    0.41
     strapping
    0.41
     jButton
    0.41
    ALBERT
    0.40
     REPORT
    0.40
    വി
    0.39
    /),
    0.39
    POSITIVE LOGITS
    bart
    0.56
    gebnis
    0.50
    ologisch
    0.50
     Tanto
    0.50
    yemek
    0.48
     yakın
    0.48
    olojik
    0.48
     نظر
    0.47
     儿
    0.47
    kim
    0.46
    Activations Density 0.000%

    No Known Activations