© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64398
    Prev
    Next
    INDEX
    Explanations

    sporting events and games

    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
     arc
    -0.69
    ittles
    -0.69
    punkt
    -0.68
     JEE
    -0.68
    ICLE
    -0.68
    ミノ
    -0.67
     cá
    -0.67
    órico
    -0.66
    vels
    -0.65
    reich
    -0.65
    POSITIVE LOGITS
     live
    1.24
     leagues
    1.16
     events
    1.14
     markets
    1.09
    events
    1.07
     league
    1.04
     competitions
    1.03
    live
    1.03
     sporting
    1.02
    Fixture
    0.98
    Activations Density 0.011%

    No Known Activations