© 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. 195222
    Prev
    Next
    INDEX
    Explanations

    prepare yourself

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

    entity, attribute, value, cell, government

    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
    찾
    0.50
    elems
    0.50
    TC
    0.49
    邋
    0.47
    舒适
    0.46
     علاق
    0.46
    ocon
    0.46
    dolphin
    0.45
     Stok
    0.45
    ت
    0.45
    POSITIVE LOGITS
    commonByteArray
    0.50
     returnPacket
    0.47
     décadas
    0.46
    蛐
    0.46
    вости
    0.46
    ması
    0.45
     folly
    0.44
    ＮＡ
    0.44
     bilgiler
    0.44
     covalently
    0.44
    Activations Density 0.000%

    No Known Activations