© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6931
    Prev
    Next
    INDEX
    Explanations

    specialized beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     has
    -2.00
    ’.
    -1.97
    !.
    -1.91
     ().
    -1.80
    ().
    -1.80
     solidaridad
    -1.78
    職場
    -1.77
    線が
    -1.73
     now
    -1.70
    。】
    -1.70
    POSITIVE LOGITS
     駅前
    1.91
    trying
    1.91
    龇
    1.82
     レスト
    1.82
    wiście
    1.78
     Татьяна
    1.75
    🏀
    1.75
    ㆆ
    1.74
    they
    1.72
    chem
    1.70
    Activations Density 0.000%

    No Known Activations