© 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. 58951
    Prev
    Next
    INDEX
    Explanations

    NCAA violations and rules

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

    The main thing this neuron does is find numeric tokens (digits, years, counts, and other numbers) in the text.

    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
    bium
    -0.80
     patente
    -0.78
     annoyance
    -0.73
     Firmen
    -0.72
    lytes
    -0.71
     удосто
    -0.71
     Statistical
    -0.71
    imageio
    -0.70
     maxY
    -0.69
     ordine
    -0.69
    POSITIVE LOGITS
     NCAA
    1.52
    NCAA
    1.22
     booster
    1.20
     boosters
    1.09
     rule
    1.07
     athletes
    1.05
     recruiting
    1.00
     athlete
    0.98
     rules
    0.95
     Booster
    0.94
    Activations Density 0.015%

    No Known Activations