© 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. 80638
    Prev
    Next
    INDEX
    Explanations

    spherical surface brightness

    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
    鬭
    -2.92
    ientras
    -2.63
     builds
    -2.55
    ate
    -2.41
     westfalen
    -2.34
    詎
    -2.30
    ’;
    -2.30
    as
    -2.27
     gewi
    -2.27
     Our
    -2.22
    POSITIVE LOGITS
    ஂ
    2.98
    ࿚
    2.78
     ihre
    2.77
     They
    2.73
     Their
    2.67
    ୌ
    2.61
    镚
    2.61
     acquire
    2.55
     legendary
    2.52
     reinforce
    2.50
    Activations Density 0.021%

    No Known Activations