© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13901
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens, especially floating‐point or large numerical values.

    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_24_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
    溶解
    0.70
     katol
    0.68
    豇
    0.63
     HIST
    0.63
     KFC
    0.61
     الجنوب
    0.61
     backlit
    0.60
     ,
    0.60
    GYPT
    0.59
     warfarin
    0.59
    POSITIVE LOGITS
    Trace
    0.62
    icians
    0.61
     ministère
    0.60
    दमी
    0.57
     énon
    0.57
     stric
    0.56
    äder
    0.55
    ifiable
    0.55
     Константи
    0.55
    िकी
    0.52
    Activations Density 0.000%

    No Known Activations