© 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. 104964
    Prev
    Next
    INDEX
    Explanations

    product, surfing, sticker

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

    fell over

    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
     قیامت
    0.49
    гә
    0.45
    ләре
    0.44
     экологи
    0.42
    พ
    0.42
    PlayerSelector
    0.41
     انك
    0.41
    ந
    0.40
     เรียน
    0.40
    қи
    0.40
    POSITIVE LOGITS
     MCD
    0.46
     neke
    0.45
    ेंसी
    0.42
    治
    0.42
     mellow
    0.41
    （
    0.41
    asius
    0.40
    </sub>
    0.40
     twe
    0.40
    是一名
    0.39
    Activations Density 0.000%

    No Known Activations