© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13694
    Prev
    Next
    INDEX
    Explanations

    car categories and brands

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

    The neuron fires on numeric expressions—sequences of digits (often with hyphens or units) like model numbers, years, measurements, and other numerical specs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     জাপান
    0.96
    Mitsubishi
    0.86
     япон
    0.86
     giapp
    0.84
    🍵
    0.84
    🥟
    0.84
    🗻
    0.84
    💶
    0.82
    🍙
    0.80
    🎌
    0.80
    POSITIVE LOGITS
     Saginaw
    1.03
     Pontiac
    0.85
     Sandusky
    0.81
     Oklahoma
    0.80
     Chevrolet
    0.80
     Buick
    0.77
     Alabama
    0.76
     Arkansas
    0.76
     truck
    0.75
     Chevy
    0.75
    Activations Density 0.354%

    No Known Activations