© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41203
    Prev
    Next
    INDEX
    Explanations

    requires that

    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
        
    -2.31
     removes
    -2.02
     In
    -2.00
    <bos>
    -1.98
     wants
    -1.93
    瀝
    -1.84
    .
    -1.84
     took
    -1.77
    WAUKEE
    -1.77
     
    -1.77
    POSITIVE LOGITS
    皤
    2.33
     ſaid
    2.09
     profond
    2.06
    
    2.00
    鷓
    1.95
     solide
    1.91
     efektif
    1.87
    м
    1.87
    isées
    1.86
     amie
    1.86
    Activations Density 0.020%

    No Known Activations