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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102038
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     \&
    -2.14
     веке
    -1.97
    ments
    -1.84
    
    -1.84
    (
    -1.82
    TintMode
    -1.80
                    
    -1.80
     sont
    -1.77
     herbs
    -1.77
    getMenuInflater
    -1.73
    POSITIVE LOGITS
     superfí
    1.97
     disponibilità
    1.91
     was
    1.88
     käytet
    1.88
     ERSITY
    1.87
    
    1.82
    或许
    1.79
     knows
    1.77
     剧照
    1.77
     However
    1.76
    Activations Density 0.003%

    No Known Activations