Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8383
    Prev
    Next
    INDEX
    Explanations

    race analysis and predictions

    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
     tháng
    -0.82
    ßerdem
    -0.78
     Objectives
    -0.75
    蔥
    -0.75
     ऐसे
    -0.73
     uszkod
    -0.72
    chufe
    -0.72
    ovou
    -0.72
     FAQ
    -0.72
     conexión
    -0.72
    POSITIVE LOGITS
     predicted
    1.01
     forecast
    0.95
     forecasts
    0.94
     runners
    0.86
     race
    0.84
     expected
    0.83
     analysis
    0.82
     morning
    0.81
     analyses
    0.81
    当日
    0.80
    Activations Density 0.015%

    No Known Activations