© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5847
    Prev
    Next
    INDEX
    Explanations

    mathematical notation (`{`, `≤`, `\boxed`)

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

    The neuron chiefly detects mathematical expressions and numeric formula notation (e.g. inline equations, symbols, and numbers in formula contexts).

    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
     Ft
    0.71
     (<
    0.65
     (§
    0.63
    }/
    0.62
    <code>
    0.60
    )/
    0.60
     PSR
    0.60
    <sup>
    0.59
     eso
    0.59
     ((*
    0.59
    POSITIVE LOGITS
    {\
    1.23
     \;
    1.08
     \
    1.00
     {\
    0.96
     \,\
    0.93
    ^{\
    0.91
    _{\
    0.89
    ^{[
    0.89
    ^{
    0.85
    \,\
    0.85
    Activations Density 0.018%

    No Known Activations