© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47710
    Prev
    Next
    INDEX
    Explanations

    football leagues and cups

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

    The neuron strongly activates on numeric tokens—especially four‐digit year mentions.

    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
     polluting
    -0.79
     плит
    -0.77
     اكتوبر
    -0.77
    螨
    -0.75
     regulate
    -0.75
    каче
    -0.74
     station
    -0.73
     دیکھیے
    -0.73
    prises
    -0.72
     stations
    -0.72
    POSITIVE LOGITS
     Europa
    1.78
    Europa
    1.59
     Copa
    1.48
     cup
    1.34
     League
    1.34
     Champions
    1.32
     Cup
    1.23
     European
    1.20
     FA
    1.15
     UEFA
    1.14
    Activations Density 0.042%

    No Known Activations