© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    soccer and sports actions

    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
    Basketball
    -0.98
     Basketball
    -0.87
     Mayweather
    -0.84
    ربای
    -0.84
     Knicks
    -0.83
     bowling
    -0.83
    InputData
    -0.82
     Marlins
    -0.81
    pcm
    -0.81
    Ár
    -0.81
    POSITIVE LOGITS
     soccer
    1.96
     midfielder
    1.84
     goalkeeper
    1.76
     midfield
    1.68
     goal
    1.68
     Soccer
    1.64
     goals
    1.58
    Soccer
    1.47
    Goal
    1.39
     FIFA
    1.39
    Activations Density 0.048%

    No Known Activations