© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8248
    Prev
    Next
    INDEX
    Explanations

    C programming language standard library

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

    The neuron strongly activates on C/C++ header‐include tokens—i.e. file names or paths enclosed in angle brackets (like `<ogg/ogg.h>`).

    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
    objectManager
    0.61
    沪
    0.57
    ostream
    0.56
    CXX
    0.55
    istream
    0.53
    зре
    0.52
    Classe
    0.52
     setattr
    0.52
    炰
    0.52
    Cz
    0.51
    POSITIVE LOGITS
    typedef
    1.13
     typedef
    0.93
    stdlib
    0.89
    ctype
    0.68
     malloc
    0.65
    stdint
    0.60
     Defining
    0.60
     "#
    0.59
     prototyp
    0.58
    raints
    0.57
    Activations Density 0.013%

    No Known Activations