© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric expressions and measurements (numbers, percentages, decimals, and units).

    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
    𒁉
    0.74
     तकरीबन
    0.70
     ಅನೇಕ
    0.70
    uradaki
    0.70
     धर्मशाला
    0.69
     আবারো
    0.68
     হতাশ
    0.67
     inactivació
    0.66
    䤚
    0.65
    ዷ
    0.65
    POSITIVE LOGITS
    /
    1.03
     (
    0.91
    ↵
    0.83
     or
    0.83
    .
    0.77
    (
    0.76
    ↵↵
    0.75
    ;
    0.70
     respectively
    0.70
    /(
    0.65
    Activations Density 1.354%

    No Known Activations