© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7936
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric tokens—especially floating-point numbers, dashes, and other numerical 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
     Pty
    0.54
     Hockey
    0.52
     (/
    0.52
     Puppet
    0.49
    ﺨ
    0.49
     Masonic
    0.49
     IELTS
    0.48
     发表于
    0.48
     (=
    0.48
     scholarly
    0.48
    POSITIVE LOGITS
    他们的
    0.78
    他們的
    0.76
    *((*
    0.73
    Their
    0.71
     ihres
    0.68
     घरवालों
    0.67
     их
    0.67
    พวกเขา
    0.66
    lastval
    0.66
    their
    0.65
    Activations Density 0.015%

    No Known Activations