© 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. 1629
    Prev
    Next
    INDEX
    Explanations

    division or range separator

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

    The neuron strongly activates on digit‐containing tokens (numbers, fractions, and measurement units) in the text.

    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
     Перейти
    0.73
    ――
    0.68
     একথা
    0.67
    そういう
    0.66
    ──
    0.65
    惹
    0.57
     అంటే
    0.55
    mtable
    0.54
    $-$,
    0.53
    说道
    0.53
    POSITIVE LOGITS
    /
    4.63
     /
    3.30
    /(
    3.17
    /_
    3.16
    ／
    3.14
    /"
    3.06
    /{
    3.06
    /[
    3.06
    /...
    3.03
    /.
    3.02
    Activations Density 0.371%

    No Known Activations