© 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. 205390
    Prev
    Next
    INDEX
    Explanations

    security of, attack on, Russian Antique

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

    based on data, examples, format

    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
    .
    0.50
     decreed
    0.47
    س
    0.46
    ulen
    0.45
    เรา
    0.44
     употре
    0.44
     terapi
    0.44
     Erkrank
    0.44
    us
    0.43
    الم
    0.43
    POSITIVE LOGITS
     conjuntos
    0.46
    しい
    0.46
     vườn
    0.46
    ී
    0.45
    ḓ
    0.45
     fieldContext
    0.45
    っぽい
    0.45
     VECTOR
    0.45
     vector
    0.44
     maf
    0.44
    Activations Density 0.000%

    No Known Activations