© 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. 65033
    Prev
    Next
    INDEX
    Explanations

    #include, conventional, this

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

    The neuron activates strongly on lines that look like code import or include directives (e.g. “#include …”, `import …`, file‐extension headers).

    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
     nghĩ
    -0.87
     Notify
    -0.72
    телен
    -0.71
     bays
    -0.70
     hyal
    -0.69
    діть
    -0.69
     Worry
    -0.68
     гг
    -0.68
     sensibilities
    -0.68
     MED
    -0.68
    POSITIVE LOGITS
    Console
    0.99
     console
    0.94
     Console
    0.92
    console
    0.90
    CONSOLE
    0.90
    COORD
    0.81
    Xbox
    0.77
     FORE
    0.75
    toJSON
    0.74
     CON
    0.73
    Activations Density 0.013%

    No Known Activations