© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7268
    Prev
    Next
    INDEX
    Explanations

    attached link copy screenshot photographing pages

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

    The neuron detects mentions of reproducing or duplicating documents, such as “print” and “copy.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    非常的
    0.84
     väldigt
    0.71
     basicamente
    0.68
     дуже
    0.64
    ależy
    0.63
    很
    0.63
     상당히
    0.63
     약간
    0.62
    人了
    0.62
     খুবই
    0.60
    POSITIVE LOGITS
    <unused2197>
    0.74
     svoje
    0.68
     neoliberal
    0.65
     Riemann
    0.64
     свого
    0.64
     כדי
    0.63
     swojego
    0.63
     incriminating
    0.63
     of
    0.62
     чтобы
    0.62
    Activations Density 0.006%

    No Known Activations