© 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. 60039
    Prev
    Next
    INDEX
    Explanations

    author, copyright, list

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

    The neuron strongly activates on C/C++ preprocessor directives—especially include guards (e.g. “#ifndef…_INCLUDED__” and matching “#define”) and related “#include” lines.

    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
    Ме
    -0.72
    golang
    -0.70
    JVM
    -0.69
    以来
    -0.68
     ポ
    -0.67
    OCITY
    -0.66
     Prix
    -0.65
     проблем
    -0.65
    宵
    -0.65
    сред
    -0.64
    POSITIVE LOGITS
    coloured
    0.76
    อร
    0.68
    pared
    0.67
    bomber
    0.65
    tasting
    0.64
    ortment
    0.63
    を押
    0.63
    дук
    0.63
     đáng
    0.62
     quang
    0.62
    Activations Density 0.048%

    No Known Activations