© 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. 10-GEMMASCOPE-RES-131K
    7. 111384
    Prev
    Next
    INDEX
    Explanations

    varsity and JV contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron spotlights mentions of school sports team levels (e.g., “varsity,” “JV,” and related team designations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    餍
    -3.27
    譟
    -3.03
    
    -2.84
    阇
    -2.67
    慊
    -2.61
    扨
    -2.61
     unſ
    -2.58
    馓
    -2.56
    
    -2.48
    嗩
    -2.48
    POSITIVE LOGITS
    _
    3.09
    s
    3.00
    )
    2.95
    This
    2.91
    ﾍ
    2.86
    While
    2.84
    When
    2.81
    During
    2.80
    Despite
    2.70
     When
    2.45
    Activations Density 0.003%

    No Known Activations