© 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. 21536
    Prev
    Next
    INDEX
    Explanations

    `name` or `string` attributes

    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
    ');
    
    -1.22
    );
    
    -1.20
     those
    -1.18
    จะเป็น
    -1.14
    ;
    
    -1.12
    雳
    -1.11
     also
    -1.11
    ));
    -1.10
    );
    -1.09
    álló
    -1.08
    POSITIVE LOGITS
    0
    1.20
    はこんな感じ
    1.16
     mitig
    1.14
    especially
    1.11
     morto
    1.11
    𝒊
    1.09
     但是
    1.09
    彼が
    1.09
     должны
    1.09
     especialmente
    1.09
    Activations Density 0.031%

    No Known Activations