© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128095
    Prev
    Next
    INDEX
    Explanations

    opening or closing quotation marks

    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
    ']
    
    -1.52
    "]();
    -1.49
    );*/
    -1.47
    '];
    -1.45
    ։
    -1.44
    '};
    -1.42
     "];
    -1.39
    湄
    -1.39
    》。
    -1.38
    );
    
    
    -1.37
    POSITIVE LOGITS
    0
    1.57
    7
    1.33
    が付
    1.23
    を紹介します
    1.23
     être
    1.18
    _
    1.17
     autre
    1.16
     diferentes
    1.14
    etc
    1.14
     différentes
    1.13
    Activations Density 0.015%

    No Known Activations