© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13694
    Prev
    Next
    INDEX
    Explanations

    c++ std namespace static

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

    The neuron fires on tokens that introduce or declare named elements—e.g. namespace/xmlns declarations in XML and keywords like static, const, namespace, global (and their accompanying punctuation) in code.

    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_24_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
    ма
    0.84
    泱
    0.82
     sleepy
    0.82
     Businessman
    0.82
     embora
    0.80
    我认为
    0.80
    т
    0.80
    ку
    0.80
     webhook
    0.79
    ﻢ
    0.79
    POSITIVE LOGITS
     Nucleaire
    0.78
    på
    0.72
    ungen
    0.70
    udos
    0.70
    agility
    0.70
    ilitary
    0.69
     सगळे
    0.68
    ug
    0.68
    intra
    0.68
    atics
    0.67
    Activations Density 0.006%

    No Known Activations