© 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. 5325
    Prev
    Next
    INDEX
    Explanations

    assignments with equals sign

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

    This neuron fires on isolated technical identifiers or option names (e.g. single‐word parameters, variable or flag names) in code/config contexts.

    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
    HttpRequest
    0.59
    TextBlock
    0.59
    ここに
    0.57
    Yet
    0.55
    誐
    0.54
    VideoStream
    0.54
    ページ
    0.54
     页
    0.53
    偪
    0.52
    deprecated
    0.51
    POSITIVE LOGITS
    =
    1.15
    ={
    1.06
    =<
    1.06
    =[
    1.05
    =$
    1.00
    =-
    1.00
    =${
    0.96
     ={
    0.94
     =
    0.94
    =.
    0.93
    Activations Density 0.000%

    No Known Activations