© 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. 38412
    Prev
    Next
    INDEX
    Explanations

    betting points and spreads

    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
    addListener
    -0.79
     Arbeitgeber
    -0.77
     профиль
    -0.74
    endimento
    -0.74
    ējās
    -0.73
    |+\
    -0.73
     erstmals
    -0.73
     profit
    -0.72
     Autoren
    -0.71
    ար
    -0.70
    POSITIVE LOGITS
     points
    1.04
     spread
    1.00
    points
    0.94
     spreads
    0.94
     LINE
    0.93
     línea
    0.92
     closing
    0.91
    closing
    0.90
    POINTS
    0.88
     touchdown
    0.87
    Activations Density 0.010%

    No Known Activations