© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    section header lists, descriptions in parentheses

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

    The neuron fires on numeric tokens—especially floating-point numbers (stats, measurements, etc.) represented with decimal points.

    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
     ТО
    0.50
     ДО
    0.49
     ANY
    0.48
     \%
    0.48
     UNIX
    0.48
     NO
    0.48
     \"
    0.47
    !');
    0.47
     REQUIRE
    0.47
     желательно
    0.47
    POSITIVE LOGITS
     debuted
    0.79
     debuting
    0.71
     eponymous
    0.70
     anunció
    0.69
    此前
    0.68
     erstwhile
    0.68
    chairman
    0.67
     convirtió
    0.67
     célèbre
    0.67
     namesake
    0.67
    Activations Density 0.143%

    No Known Activations