© 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. 34-GEMMASCOPE-RES-131K
    4. 11888
    Prev
    Next
    INDEX
    Explanations

    using namespace std

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

    The neuron strongly activates on the “std” token in C++ namespace or using-namespace declarations, i.e. occurrences of the standard library namespace.

    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
    abaza
    -0.88
     worth
    -0.85
    上記
    -0.82
    навли
    -0.81
     letzt
    -0.81
     True
    -0.80
    ICULO
    -0.79
     Are
    -0.78
     każdy
    -0.77
    erals
    -0.76
    POSITIVE LOGITS
     comedor
    0.98
     compañeros
    0.96
    literals
    0.91
    withCredentials
    0.89
     muchacha
    0.85
    ⭐️
    0.85
    multer
    0.85
     Outils
    0.84
     excellente
    0.84
    ::
    0.84
    Activations Density 0.006%

    No Known Activations