© 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. 6090
    Prev
    Next
    INDEX
    Explanations

    outputting code

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

    The neuron activates on programming‐language code lines—especially function definitions and other code statements (e.g. “def …” or shell commands).

    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
     var
    0.92
     //
    0.90
    var
    0.86
     i
    0.80
     parseInt
    0.80
     /*
    0.78
     int
    0.77
     /**
    0.76
     {//
    0.76
     ArrayList
    0.75
    POSITIVE LOGITS
    getattr
    0.77
    Мак
    0.66
    Del
    0.63
     संवैधानिक
    0.60
    ᚑ
    0.60
     descripción
    0.59
    अधिक
    0.59
    del
    0.58
     фран
    0.58
    SRPC
    0.58
    Activations Density 0.000%

    No Known Activations