© 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. 1776
    Prev
    Next
    INDEX
    Explanations

    function arguments

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

    The neuron selectively fires on numeric tokens, especially floating‐point numbers (i.e. numbers 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
    z
    0.49
    \}$
    0.48
    )(((
    0.48
    ['
    0.46
    array
    0.45
    q
    0.45
    Var
    0.45
    )^{
    0.44
     \
    0.44
    ^{
    0.43
    POSITIVE LOGITS
     with
    0.79
     for
    0.70
    的其他
    0.67
     doğrud
    0.63
     regarding
    0.62
     featuring
    0.61
     kanggo
    0.61
     vía
    0.61
     dyslex
    0.61
     inversa
    0.59
    Activations Density 0.001%

    No Known Activations