© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1222
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on programming code syntax—i.e. tokens belonging to code blocks such as function definitions, method calls, parentheses, assignments, etc.

    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
     zaken
    0.52
     politic
    0.49
    businessman
    0.49
    वेश
    0.49
    تاریخ
    0.49
    ओं
    0.49
    în
    0.49
    飯
    0.48
    Boolean
    0.47
    HttpServlet
    0.47
    POSITIVE LOGITS
     //
    1.54
    ;//
    1.51
    ();//
    1.48
    ++;//
    1.41
     {//
    1.39
    ];//
    1.34
     //=>
    1.29
    ');//
    1.29
    ");//
    1.28
    ";//
    1.27
    Activations Density 0.002%

    No Known Activations