© 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. 22-GEMMASCOPE-RES-131K
    7. 127979
    Prev
    Next
    INDEX
    Explanations

    exclusive interviews, features, and offers

    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_22/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
    ↵↵
    -2.72
    </i>
    -2.67
     a
    -2.48
    ]));
    -2.39
    </th>
    -2.31
     Its
    -2.19
    "));
    -2.09
    鬟
    -2.05
    }$
    -2.03
    );
    -2.02
    POSITIVE LOGITS
    ’，
    2.72
    فوائد
    2.25
    ୈ
    2.16
    𖥦
    2.13
    韞
    2.08
    酲
    2.06
    ကိုးကား
    2.05
     總
    2.02
    Виды
    2.02
    Despite
    2.02
    Activations Density 0.013%

    No Known Activations