© 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. 9289
    Prev
    Next
    INDEX
    Explanations

    tom brady's performance and human performance metrics

    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
     stout
    -1.21
     pintado
    -1.13
    较为
    -1.12
    Datetime
    -1.12
     heroin
    -1.10
    Stil
    -1.08
     gustan
    -1.07
    
    -1.06
    讷
    -1.06
    秸
    -1.05
    POSITIVE LOGITS
     ultimately
    1.46
     tecnologías
    1.37
     increasingly
    1.27
     eventually
    1.22
     通过
    1.14
     increase
    1.13
     modificaciones
    1.13
    も行
    1.10
     changes
    1.10
     variaciones
    1.09
    Activations Density 0.110%

    No Known Activations