© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93050
    Prev
    Next
    INDEX
    Explanations

    C++ standard library `std::chrono`

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

    The neuron activates on C++ timing code using the `<chrono>` library (e.g. includes and namespace or function calls involving chrono).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     virtualization
    -0.80
     должен
    -0.73
     verursacht
    -0.73
     sollte
    -0.72
    érir
    -0.71
     crashes
    -0.71
    달
    -0.69
    win
    -0.69
    </blockquote>
    -0.68
    moz
    -0.68
    POSITIVE LOGITS
     chrono
    0.87
     std
    0.82
    wunsch
    0.82
    Содержание
    0.81
     olie
    0.81
     [](
    0.79
    chrono
    0.79
     high
    0.79
    std
    0.77
     typedef
    0.77
    Activations Density 0.032%

    No Known Activations