© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9522
    Prev
    Next
    INDEX
    Explanations

    copying, duplicating, reproduction

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

    copying

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

    copy

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赜
    0.41
    çam
    0.41
    辕
    0.40
    粝
    0.38
    ẵn
    0.37
    ণাস্ত্র
    0.37
    RequestParam
    0.37
     راجس
    0.37
    <0xBE>
    0.36
    Ǻ
    0.36
    POSITIVE LOGITS
     copy
    3.55
     copying
    3.53
     copied
    3.39
     Copy
    3.33
    copy
    3.31
     копи
    3.22
    Copy
    3.16
     COPY
    3.13
    复制
    3.08
    コピー
    3.08
    Activations Density 0.304%

    No Known Activations