© 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. 114139
    Prev
    Next
    INDEX
    Explanations

    announcements and notable events

    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
    !"
    -2.55
    ?"
    -2.48
    ,"
    -2.47
    」
    -2.13
    ）
    -2.13
    );
    -2.11
    ];
    -2.05
    )."
    -1.98
    ?'
    -1.94
    ”;
    -1.93
    POSITIVE LOGITS
    O
    2.06
    ндарт
    2.00
    畬
    1.73
    ⦊
    1.70
    鬟
    1.70
     besar
    1.70
    鈈
    1.67
    ne
    1.59
    ⃨
    1.59
    鵟
    1.56
    Activations Density 0.027%

    No Known Activations