© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19605
    Prev
    Next
    INDEX
    Explanations

    virtual, static, operator in code

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

    The neuron detects C++ member‐function declaration specifiers (e.g. “virtual,” “static,” “operator,” and the destructor “~”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -3.03
    ним
    -2.00
     \
    -1.96
    if
    -1.82
    ("
    -1.70
    ・
    -1.68
     with
    -1.57
    จาก
    -1.53
    +/**
    -1.52
    км
    -1.52
    POSITIVE LOGITS
    Apparently
    1.68
    Surely
    1.63
    觧
    1.56
    汌
    1.49
     parfaite
    1.47
    羕
    1.45
     plomo
    1.44
    Trying
    1.44
    
    1.44
     ビル
    1.43
    Activations Density 0.002%

    No Known Activations