© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20018
    Prev
    Next
    INDEX
    Explanations

    std::cout, std::string, std::endl

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

    The neuron activates on occurrences of C++ scope‐resolution operators (token “::”), especially in “std::” library qualifiers.

    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
    },
    -1.59
    ’,
    -1.56
     Each
    -1.53
     даже
    -1.48
     chỉ
    -1.46
     have
    -1.43
     весь
    -1.41
     hanya
    -1.41
    href
    -1.40
    并
    -1.40
    POSITIVE LOGITS
     berücksich
    1.66
     glaubte
    1.65
     wüns
    1.65
     niektórych
    1.61
     maquiagem
    1.61
    鲧
    1.60
     erwäh
    1.54
    pearance
    1.51
     swojej
    1.51
    
    1.49
    Activations Density 0.002%

    No Known Activations