© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6870
    Prev
    Next
    INDEX
    Explanations

    network messages and code structure

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

    The neuron fires on C/C++‐style code syntax, especially preprocessor directives (#include), comments (//), header file names (“.h”), and the scope resolution operator (::).

    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
    ásban
    -0.80
     Tél
    -0.79
    iae
    -0.77
    grenze
    -0.77
    upuesto
    -0.77
    umpulkan
    -0.77
     Conseils
    -0.77
    ով
    -0.76
    zeko
    -0.75
    énage
    -0.74
    POSITIVE LOGITS
     notify
    0.82
     Ack
    0.82
    Syn
    0.81
     hart
    0.81
    同步
    0.80
     syn
    0.79
    syn
    0.77
    ниме
    0.76
    ack
    0.75
     response
    0.75
    Activations Density 0.003%

    No Known Activations