© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58939
    Prev
    Next
    INDEX
    Explanations

    either side

    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
    </strong>
    -1.98
     where
    -1.68
    ↵↵
    -1.68
     {
    -1.66
     &
    -1.54
    Where
    -1.54
    .
    -1.52
    );
    -1.48
    {
    -1.46
                    
    -1.45
    POSITIVE LOGITS
    
    1.62
    沄
    1.47
    的气息
    1.45
    
    1.41
     genoemd
    1.38
    灩
    1.36
    棪
    1.36
     dramatique
    1.35
    Namun
    1.34
    محمد
    1.34
    Activations Density 0.011%

    No Known Activations