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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 561
    Prev
    Next
    INDEX
    Explanations

    staying up to date

    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
     to
    -1.73
     aislada
    -1.49
     venerable
    -1.45
    uarine
    -1.45
     thorny
    -1.44
     namorados
    -1.41
    ylase
    -1.37
     ก็
    -1.35
    <h2>
    -1.34
     cabelos
    -1.34
    POSITIVE LOGITS
     of
    1.95
    
    1.75
    梣
    1.59
    旒
    1.45
     paulo
    1.39
     changes
    1.37
     updates
    1.36
     çik
    1.35
    ᯅ
    1.34
     rouges
    1.34
    Activations Density 0.022%

    No Known Activations