© 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. 222476
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    URLs and concepts following specific words

    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
    িয়৷
    0.52
    blox
    0.50
    salmon
    0.46
    بيع
    0.45
    outlet
    0.45
    BUY
    0.44
     mobilité
    0.44
     engages
    0.43
    indeed
    0.43
     giết
    0.43
    POSITIVE LOGITS
    หว
    0.46
    中華
    0.44
     Cochrane
    0.44
    ける
    0.44
    ้น
    0.44
    데
    0.44
    чить
    0.44
     অসুবিধা
    0.43
    త్రి
    0.43
    ο
    0.43
    Activations Density 0.000%

    No Known Activations