© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208049
    Prev
    Next
    INDEX
    Explanations

    a logical unit

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

    age difference

    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
    Negative Logits
     proposés
    0.52
    草原
    0.48
    मताओं
    0.46
    Bev
    0.46
     விவசாயிகள்
    0.45
    艇
    0.45
     नेताओं
    0.44
     الدفاع
    0.44
    اليا
    0.44
    出行
    0.44
    POSITIVE LOGITS
    ual
    0.48
    .
    0.47
     Spirit
    0.46
    <0x0D>
    0.45
     renal
    0.45
     h
    0.44
     Avatar
    0.44
    ERR
    0.43
    </h2>
    0.42
     incarnation
    0.42
    Activations Density 0.000%

    No Known Activations