© 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. 70175
    Prev
    Next
    INDEX
    Explanations

    FIFA World Cup scores and years

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

    The neuron activates on numeric year mentions (especially four-digit years) in sports contexts such as “in 1974 FIFA World Cup.”

    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
     November
    -0.96
     October
    -0.93
     February
    -0.86
     September
    -0.84
     December
    -0.74
    ateľ
    -0.73
    scott
    -0.73
     January
    -0.73
     Shelves
    -0.71
     клуб
    -0.70
    POSITIVE LOGITS
     FIFA
    1.00
    Italia
    0.91
     Germany
    0.90
     Italia
    0.89
     Fifa
    0.85
     Brazil
    0.84
    Qc
    0.82
     Mundial
    0.80
    Germany
    0.80
     France
    0.78
    Activations Density 0.019%

    No Known Activations