© 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. 10-GEMMASCOPE-RES-131K
    7. 112895
    Prev
    Next
    INDEX
    Explanations

    ownership and accountability

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

    The main thing this neuron does is find legal-ownership or copyright/property statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     rallado
    -1.22
    天氣
    -1.18
     étages
    -1.17
    אח
    -1.16
     perched
    -1.11
     würde
    -1.11
    tactos
    -1.11
     sentiers
    -1.11
     記念
    -1.10
    ขอ
    -1.10
    POSITIVE LOGITS
     by
    1.95
    鴣
    1.46
    啬
    1.41
    although
    1.39
    entire
    1.34
    又不
    1.30
    おもしろ
    1.30
     beeinf
    1.29
    нечно
    1.28
    *************/
    1.25
    Activations Density 0.064%

    No Known Activations