© 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. 34-GEMMASCOPE-RES-131K
    7. 76824
    Prev
    Next
    INDEX
    Explanations

    c++ include statements

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

    The neuron is strongly activated by C/C++ preprocessor directives (lines beginning with “#”).

    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
     kuasa
    -0.87
    ラの
    -0.81
     bardak
    -0.77
    Já
    -0.75
    CreatedAt
    -0.75
     radikal
    -0.75
    Aktiv
    -0.74
     podría
    -0.74
    chem
    -0.74
     olas
    -0.73
    POSITIVE LOGITS
     Mojo
    0.85
     mojo
    0.84
    Prove
    0.82
     sliders
    0.79
    素
    0.78
     служ
    0.76
     Zebra
    0.75
    ⎨
    0.75
     Gators
    0.73
     Prove
    0.73
    Activations Density 0.052%

    No Known Activations