© 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. 13903
    Prev
    Next
    INDEX
    Explanations

    data keys and labels

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

    The neuron strongly activates on technical field or parameter names (often in uppercase or title case) used as labels in API or configuration reference tables.

    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
    ঙে
    0.63
    猪
    0.63
     کردن
    0.61
     করে
    0.61
     архіви
    0.61
    ross
    0.60
    hanti
    0.59
     करून
    0.58
    촬
    0.58
    outil
    0.58
    POSITIVE LOGITS
     ids
    0.71
    Ids
    0.64
     percentage
    0.63
     thumbnailUrl
    0.61
     _
    0.61
     {
    0.59
     [
    0.58
     {\
    0.57
     Pequ
    0.55
     [{'
    0.55
    Activations Density 0.027%

    No Known Activations