© 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. 86929
    Prev
    Next
    INDEX
    Explanations

    laced up

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

    modelrelease, delta, and author

    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
    ਿ
    0.52
    زاء
    0.50
    arq
    0.48
    digos
    0.48
     игра
    0.47
     iguais
    0.47
    okkh
    0.46
    trä
    0.46
    िज
    0.46
    稱
    0.45
    POSITIVE LOGITS
    </h2>
    0.50
    <0x0D>
    0.49
     મ
    0.48
     Ulster
    0.48
     Hindustan
    0.47
     lewis
    0.46
    seg
    0.45
    Picklist
    0.45
     Lincoln
    0.44
    Acetoxy
    0.44
    Activations Density 0.002%

    No Known Activations