© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12663
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric data—quantities, measurements, counts, and other number tokens.

    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
    Không
    0.57
     만들
    0.55
    儅
    0.55
     cưới
    0.55
    ceding
    0.54
     menikah
    0.54
    北部
    0.54
     써
    0.54
    adakan
    0.54
    用餐
    0.53
    POSITIVE LOGITS
     dwóch
    0.64
     might
    0.62
     Fiz
    0.56
     అవ
    0.55
     Imag
    0.55
    art
    0.54
     poco
    0.54
    IVO
    0.54
    UA
    0.53
     bele
    0.53
    Activations Density 0.002%

    No Known Activations