© 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. 12102
    Prev
    Next
    INDEX
    Explanations

    American football teams and players

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

    The main thing this neuron does is detect numeric tokens (multi‐digit numbers) such as years, scores, and statistical figures.

    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
    Wednesday
    -0.91
    NBA
    -0.80
    inkler
    -0.77
    Tuesday
    -0.77
     NBA
    -0.77
    érape
    -0.75
     Bundesliga
    -0.73
    名的
    -0.71
     labours
    -0.69
    Girls
    -0.68
    POSITIVE LOGITS
    🏈
    1.22
     football
    1.16
     FCS
    0.96
    sack
    0.96
    imura
    0.93
     Football
    0.92
    bowl
    0.92
     FOOTBALL
    0.88
     Bowl
    0.85
     sacks
    0.85
    Activations Density 0.059%

    No Known Activations