© 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. 84956
    Prev
    Next
    INDEX
    Explanations

    game and contest 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
    Dato
    -0.82
    isantes
    -0.81
    startup
    -0.79
    Goa
    -0.79
    ुष
    -0.79
     vhodné
    -0.78
    艏
    -0.76
     turbine
    -0.75
    probe
    -0.73
    alamualaikum
    -0.73
    POSITIVE LOGITS
     picks
    3.00
     picking
    2.64
     pick
    2.55
     picked
    2.48
     predictions
    2.34
    pick
    2.33
     Pick
    2.27
     Picks
    2.23
     prediction
    2.23
    Pick
    2.17
    Activations Density 0.035%

    No Known Activations