© 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. 49437
    Prev
    Next
    INDEX
    Explanations

    copy process

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Chrift
    -0.79
    🏩
    -0.77
     trơn
    -0.76
    ี้ยง
    -0.73
    ίνη
    -0.73
     ACKNOWLEDGMENTS
    -0.71
    IMAN
    -0.71
     hermoso
    -0.71
    zeppelin
    -0.70
    tilizers
    -0.70
    POSITIVE LOGITS
     copy
    4.09
     copying
    3.88
     copies
    3.86
     photocopy
    3.47
    copy
    3.47
     copied
    3.28
     Copy
    3.25
    Copy
    3.16
    COPY
    3.13
     photocopying
    3.03
    Activations Density 0.095%

    No Known Activations