© 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. 30038
    Prev
    Next
    INDEX
    Explanations

    bacteria, Newton, sales, creation, identity, competition, promising

    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
    \;
    0.46
     Casting
    0.46
    ')
    0.44
    ':
    0.44
     불구하고
    0.44
     konkre
    0.40
     člov
    0.40
     Attention
    0.40
    redd
    0.40
    riere
    0.39
    POSITIVE LOGITS
    ಿಕ
    0.50
    समु
    0.49
    𝕐
    0.48
    ブラシ
    0.48
    帽
    0.48
     predominate
    0.47
    INI
    0.46
    ÉE
    0.46
     exceptionally
    0.46
    हार्
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.