© 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. 2585
    Prev
    Next
    INDEX
    Explanations

    function calls ending in ()

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

    This neuron primarily detects programming function or library call names (e.g. commands like forward(), bye(), print(), ob_end_clean(), ob_start(), ob_get_level()).

    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
    ですので
    0.77
    ;
    0.73
     Thus
    0.71
     Therefore
    0.69
     Portanto
    0.67
     Tencent
    0.66
     portanto
    0.65
    ){
    0.65
    ませんので
    0.64
     Atelier
    0.64
    POSITIVE LOGITS
    ()
    3.28
    (),
    2.97
    ().
    2.81
    ():
    2.58
     ()
    2.52
    ()/
    2.45
    ())
    2.42
    ()-
    2.42
    ()+
    2.42
    ()`
    2.41
    Activations Density 0.131%

    No Known Activations