© 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. 9927
    Prev
    Next
    INDEX
    Explanations

    mathematical assignments or equations

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

    The neuron consistently fires on numeric measurement tokens (especially decimal numbers and statistical 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_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
     +
    1.16
     +=
    0.89
     {
    0.85
     |
    0.83
     ->
    0.80
     +(
    0.80
     ||
    0.79
     ×
    0.79
     //
    0.73
     |=
    0.73
    POSITIVE LOGITS
    =/
    0.79
    =[],
    0.76
    =}
    0.71
    ranu
    0.70
    =*
    0.68
    includes
    0.68
    administrator
    0.68
    =");
    0.66
    /).
    0.66
    =$\
    0.63
    Activations Density 0.023%

    No Known Activations