© 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. 133007
    Prev
    Next
    INDEX
    Explanations

    WeChat QQ Tencent

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

    Ghana/permissions

    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
    Whitelist
    0.47
    ColorBit
    0.46
    badbreak
    0.46
     EVAL
    0.45
     お知らせ
    0.45
     ګټ
    0.44
     விளக்கம்
    0.44
    <unused48>
    0.43
    elementProp
    0.43
    ccgi
    0.42
    POSITIVE LOGITS
     utan
    0.46
     sina
    0.45
     akan
    0.44
     Akan
    0.44
    aille
    0.42
    Organizer
    0.41
     cui
    0.41
     Hutch
    0.41
     GPS
    0.40
     mik
    0.40
    Activations Density 0.001%

    No Known Activations