© 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. 178428
    Prev
    Next
    INDEX
    Explanations

    repair, tested, performance

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

    sexual, pictures, disposal, events

    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
    чность
    0.46
    Package
    0.44
    Building
    0.44
    Meter
    0.43
    サイズの
    0.43
    Cement
    0.43
    “
    0.43
    Page
    0.43
    Product
    0.42
    Program
    0.42
    POSITIVE LOGITS
     遅く
    0.51
     イベント
    0.50
     написа
    0.49
    ר
    0.48
     интенсив
    0.46
     esempi
    0.46
     `-
    0.46
     `@
    0.45
     ചേ
    0.44
     方向
    0.43
    Activations Density 0.000%

    No Known Activations