© 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. 80891
    Prev
    Next
    INDEX
    Explanations

    bad calls and penalties

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

    The neuron fires on terminology around sports officiating and rule enforcement—references to referees/judges and the penalties or unsportsmanlike‐conduct actions they impose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Op
    -0.89
    Laws
    -0.80
    Sparks
    -0.79
     tervez
    -0.77
     Records
    -0.76
    сле
    -0.75
     planner
    -0.75
    ervé
    -0.75
    ddagger
    -0.73
     asiático
    -0.72
    POSITIVE LOGITS
     calls
    1.55
     call
    1.31
    calls
    1.29
     Calls
    1.22
    Calls
    1.22
     crew
    1.16
     calling
    1.14
    call
    1.02
    CALL
    1.01
    Crew
    0.99
    Activations Density 0.017%

    No Known Activations