© 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. 38556
    Prev
    Next
    INDEX
    Explanations

    cricket scores runs

    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
     innings
    -1.06
    gs
    -0.81
    cky
    -0.78
     centrifugation
    -0.73
    정
    -0.73
     knocks
    -0.69
    niająca
    -0.68
    找
    -0.68
    udadera
    -0.68
    申し
    -0.68
    POSITIVE LOGITS
    runs
    1.02
     runs
    1.02
     boundary
    0.96
     boundaries
    0.95
    boundaries
    0.95
    Runs
    0.85
    🤏
    0.84
     consecutive
    0.80
     Лег
    0.79
     Runs
    0.77
    Activations Density 0.007%

    No Known Activations