© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    polynomial and algebraic structures

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

    The main thing this neuron does is detect numeric tokens (numbers and digit sequences) in the text.

    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
     Baltic
    0.68
     Ragnar
    0.59
    varrho
    0.57
    renergic
    0.57
     catalase
    0.57
     balt
    0.57
    ɐ
    0.56
     বধ
    0.56
     мяс
    0.54
     kenn
    0.52
    POSITIVE LOGITS
    Polynomial
    0.80
     Polynomial
    0.76
    polynomial
    0.72
     polynomial
    0.70
     monomials
    0.69
     polynomials
    0.68
    Affine
    0.68
    Algebra
    0.64
     Zariski
    0.64
     DeConcini
    0.63
    Activations Density 0.052%

    No Known Activations