© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117487
    Prev
    Next
    INDEX
    Explanations

    plagiarism detection service

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

    The neuron strongly activates on mentions of the “Copyscape” plagiarism‐detection service (i.e. the brand name “Copyscape”).

    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
    tuous
    -0.70
     listen
    -0.70
    Deze
    -0.70
    看书
    -0.68
     categories
    -0.68
     households
    -0.68
     Irr
    -0.67
     leaflets
    -0.67
     Pros
    -0.65
     Data
    -0.65
    POSITIVE LOGITS
     originality
    1.13
     Similarity
    1.10
    Similarity
    1.10
    percentage
    1.05
     similarity
    0.99
    Detector
    0.96
    fuente
    0.94
    similarity
    0.93
     detection
    0.93
    检测
    0.92
    Activations Density 0.005%

    No Known Activations