© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5235
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to mathematical notation and formulaic expressions (numbers, variables, symbols, and references to equation components).

    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
     professionnels
    0.86
    💵
    0.84
    aurants
    0.82
    financ
    0.80
     शुरु
    0.80
     pensamientos
    0.80
    💰
    0.79
     profesionales
    0.79
     tiendas
    0.79
     ఎక్కువగా
    0.78
    POSITIVE LOGITS
     $\
    0.95
     equivalently
    0.92
     θ
    0.92
     invariant
    0.90
     $|\
    0.89
     $(\
    0.88
     $\{
    0.87
     $\{\
    0.86
     Dirichlet
    0.86
     surjective
    0.84
    Activations Density 0.086%

    No Known Activations