© 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. 34-GEMMASCOPE-RES-131K
    7. 56084
    Prev
    Next
    INDEX
    Explanations

    sports actions and outcomes

    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_34/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
    mdi
    -0.77
    prite
    -0.73
    Více
    -0.72
     odpo
    -0.71
    ghorn
    -0.71
    hibian
    -0.70
    weif
    -0.69
    erías
    -0.69
    racuse
    -0.69
    oxide
    -0.69
    POSITIVE LOGITS
     volley
    1.02
     rebound
    1.02
     overhead
    0.96
     redirection
    0.94
     control
    0.91
     redirect
    0.79
    Overhead
    0.78
     loose
    0.78
     vol
    0.78
     vole
    0.77
    Activations Density 0.015%

    No Known Activations