© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5048
    Prev
    Next
    INDEX
    Explanations

    The neuron chiefly picks out numeric values—especially decimal‐formatted measurements or statistics—in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     トート
    1.31
     取っ
    1.29
     Ï
    1.27
     スカート
    1.26
     ApJ
    1.21
     リュック
    1.21
     Ν
    1.20
     Ι
    1.19
     吴
    1.19
     Tutto
    1.17
    POSITIVE LOGITS
    //
    1.95
    (
    1.79
    {
    1.70
    $
    1.51
    "
    1.50
    "${
    1.48
    ()
    1.36
    #
    1.34
    _
    1.33
    [
    1.30
    Activations Density 0.028%

    No Known Activations