© 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. 73593
    Prev
    Next
    INDEX
    Explanations

    header guards and copyright

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

    This neuron specializes in spotting C/C++ preprocessor directives (e.g. #include, #define and their header or macro names).

    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
     nutzen
    -0.75
     કે
    -0.73
    我也是
    -0.72
     pups
    -0.71
    Semana
    -0.70
    それを
    -0.69
     маса
    -0.66
     практически
    -0.66
     mugs
    -0.66
    グラス
    -0.64
    POSITIVE LOGITS
     JU
    1.23
     ju
    1.12
    JU
    1.03
    PEER
    0.85
     Ju
    0.83
    LookAndFeel
    0.82
    嘶
    0.81
    桀
    0.79
     VST
    0.78
    もあって
    0.77
    Activations Density 0.012%

    No Known Activations