© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10193
    Prev
    Next
    INDEX
    Explanations

    type hints for str parameters

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

    The neuron consistently activates on type or class identifiers (e.g. data‐type names like String, Timestamp, Record, Fields).

    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
     ""){
    0.62
    ・・・
    0.57
    ()[
    0.54
    (){}
    0.54
     appunto
    0.54
    ･･･
    0.53
    Since
    0.52
    ()){
    0.52
    )‏
    0.52
     zau
    0.50
    POSITIVE LOGITS
     असतील
    0.61
     হইত
    0.55
     объяснить
    0.55
     کیل
    0.54
     intricately
    0.52
    പക്ഷ
    0.51
     ruining
    0.51
    Simplified
    0.51
     Judi
    0.51
     inflicting
    0.51
    Activations Density 0.003%

    No Known Activations