© 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. 12967
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for numeric tokens—especially numbers with decimal points or other numeric 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
     principalmente
    0.70
     واجب
    0.68
     NSArray
    0.68
     Encounter
    0.62
    صوص
    0.61
    JSONArray
    0.60
    NSArray
    0.59
    .([]
    0.57
     terutama
    0.57
     دائما
    0.56
    POSITIVE LOGITS
     ({
    1.70
    ({
    1.70
    ({"
    1.39
    ({'
    1.34
    ',{
    1.30
     {
    1.23
    ,{
    1.21
     [{
    1.20
    :{
    1.18
    ",{
    1.18
    Activations Density 0.007%

    No Known Activations