© 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. 38581
    Prev
    Next
    INDEX
    Explanations

    URL before colon

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

    This neuron detects the boilerplate phrase requiring that the copyright/permission notice be “included in all copies.”

    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
     took
    -0.95
    اولة
    -0.90
    公安
    -0.88
     числен
    -0.79
    毫米
    -0.77
    кистан
    -0.75
     Bör
    -0.75
     thinks
    -0.74
    entier
    -0.73
     }}$}
    -0.73
    POSITIVE LOGITS
    informe
    0.87
    หว่าง
    0.85
    liegende
    0.85
    typically
    0.84
    validates
    0.82
    ধ্য
    0.82
    laufen
    0.81
    verständnis
    0.79
     EIF
    0.78
     {@
    0.77
    Activations Density 0.001%

    No Known Activations