© 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. 5060
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    The neuron strongly activates on tokens that consist entirely of multi‐digit numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    лы
    0.44
     Listo
    0.42
    лов
    0.39
    korzyst
    0.38
    批准
    0.38
    Listo
    0.38
    ">%
    0.38
    漫
    0.38
    凝
    0.37
    ozat
    0.37
    POSITIVE LOGITS
    _
    0.41
     wallpapers
    0.41
     Immunology
    0.39
    ई
    0.38
     caution
    0.38
    edar
    0.38
     resusc
    0.36
     डिलीवरी
    0.36
     Jewelry
    0.36
     shan
    0.36
    Activations Density 0.043%

    No Known Activations