© 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. 18407
    Prev
    Next
    INDEX
    Explanations

    listings and directories

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

    negative states or limits

    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
     usage
    0.52
     broadband
    0.47
     uses
    0.46
    র্গ
    0.46
     ব্যবহারের
    0.45
    レ
    0.43
     استخدام
    0.42
     Roundtable
    0.42
     title
    0.42
     french
    0.41
    POSITIVE LOGITS
    cję
    0.49
    ździer
    0.49
    objectId
    0.47
     Екатери
    0.46
    $.;
    0.44
     защото
    0.44
     бо
    0.43
    <0x84>
    0.42
     звер
    0.42
     దృష్టి
    0.42
    Activations Density 0.000%

    No Known Activations