© 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. 22555
    Prev
    Next
    INDEX
    Explanations

    Indian and Indians

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -1.92
    });
    -1.92
    u
    -1.89
    j
    -1.77
    }
    -1.69
    '
    -1.66
    监狱
    -1.64
    My
    -1.63
    ();
    -1.62
    ?"
    -1.62
    POSITIVE LOGITS
    瘣
    2.02
    狆
    1.98
    翾
    1.96
    蒌
    1.96
    憮
    1.95
     знают
    1.94
    鹛
    1.83
    砗
    1.82
    玧
    1.82
    apatilla
    1.80
    Activations Density 0.013%

    No Known Activations