© 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. 92395
    Prev
    Next
    INDEX
    Explanations

    style and design

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

    correlate with, easy to, result in, prevalent often, spaces often

    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
     HAI
    0.56
    నిక
    0.52
     HEK
    0.51
     餐
    0.51
    HAI
    0.49
    dı
    0.48
     ERK
    0.48
    OSE
    0.48
     AAS
    0.47
    ıs
    0.47
    POSITIVE LOGITS
    پی
    0.45
     compra
    0.45
    자동차
    0.42
    css
    0.42
    पंजाब
    0.41
    ピ
    0.41
    uml
    0.41
    布
    0.40
    ":
    0.40
    build
    0.40
    Activations Density 0.000%

    No Known Activations