© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 228
    Prev
    Next
    INDEX
    Explanations

    This neuron detects multi‐digit numeric expressions (large numbers, percentages, statistics, and measurements).

    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
    。
    0.37
     Nhưng
    0.29
     ซึ่ง
    0.28
    ซึ่ง
    0.28
    ｡
    0.28
     。
    0.27
     そして
    0.27
    ។
    0.27
    ।
    0.26
    ။
    0.26
    POSITIVE LOGITS
     primarily
    0.61
     predominantly
    0.57
     исключительно
    0.57
     exclusively
    0.56
     differently
    0.55
     ausschließlich
    0.53
     wyłącznie
    0.52
     solely
    0.52
     principally
    0.51
     exclusivamente
    0.51
    Activations Density 1.500%

    No Known Activations