© 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. 6947
    Prev
    Next
    INDEX
    Explanations

    offensive and defensive play

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

    The neuron activates on mentions of sports tactics and roles, especially offensive and defensive terms in football.

    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
     defensi
    -1.30
     defensively
    -1.24
     defends
    -1.23
     defences
    -1.14
    Result
    -1.05
     defended
    -1.02
     defenders
    -0.98
    ův
    -0.96
     Defend
    -0.94
     defence
    -0.92
    POSITIVE LOGITS
    nių
    1.02
    沓
    1.02
     capabilities
    1.00
     prowess
    0.95
     esfuerzos
    0.94
     identity
    0.93
    焱
    0.93
    ⇰
    0.90
     department
    0.90
    minded
    0.90
    Activations Density 0.010%

    No Known Activations