© 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. 933
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numerical tokens, especially floating-point numbers or 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_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
     tzv
    0.66
     tzw
    0.58
     ancillary
    0.53
     U
    0.52
     $
    0.52
     •
    0.51
     Figure
    0.50
     [
    0.49
     Overview
    0.48
     primaries
    0.48
    POSITIVE LOGITS
     housework
    0.73
    ieszka
    0.69
    cheerful
    0.68
    irthday
    0.66
    cadilly
    0.65
    इकिल
    0.64
     arroz
    0.63
    bohyd
    0.63
    wać
    0.63
     admires
    0.63
    Activations Density 0.376%

    No Known Activations