© 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. 34-GEMMASCOPE-RES-131K
    7. 62697
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    butter
    -0.83
    🟡
    -0.73
    ıştır
    -0.73
    囯
    -0.72
     公司
    -0.72
    ;"></
    -0.71
     shits
    -0.71
    ႉ
    -0.71
    ABUL
    -0.71
     nyt
    -0.70
    POSITIVE LOGITS
     Sioux
    0.77
    ATED
    0.77
     South
    0.77
    VERT
    0.77
    </sup>
    0.75
    言って
    0.74
    Prof
    0.73
    </sub>
    0.72
     SOUTH
    0.71
    服务
    0.70
    Activations Density 0.018%

    No Known Activations