© 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. 170535
    Prev
    Next
    INDEX
    Explanations

    chromium plays, such class, review they

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

    dominance and devotion

    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
     حاجات
    0.44
    r
    0.44
    •
    0.43
    र
    0.42
    {$\
    0.42
     неболь
    0.42
    所谓
    0.42
    ب
    0.41
     classified
    0.41
     alterations
    0.40
    POSITIVE LOGITS
     ഞങ്ങൾ
    0.50
    🤩
    0.48
     stripos
    0.47
     국내
    0.46
     커피
    0.46
    ანი
    0.45
     🥰
    0.45
     libri
    0.45
     necesitamos
    0.44
     chahiye
    0.44
    Activations Density 0.000%

    No Known Activations