© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1789
    Prev
    Next
    INDEX
    Explanations

    numeric citations

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

    The neuron consistently fires on numeric tokens—especially floating‐point numbers or multi‐digit 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
     =
    0.71
     -
    0.70
     voy
    0.68
     position
    0.67
     set
    0.64
     game
    0.64
     comportamiento
    0.63
     pensando
    0.62
     haka
    0.62
     tous
    0.61
    POSITIVE LOGITS
    $^{
    0.70
    <sup>
    0.67
     $^{
    0.66
    footnote
    0.64
     }^{[
    0.64
     Additionally
    0.62
     Ibid
    0.62
    ],”
    0.61
    ۱
    0.61
    ᱘
    0.58
    Activations Density 0.013%

    No Known Activations