© 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. 22-GEMMASCOPE-RES-131K
    7. 128954
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on verbs that denote transferring or relocating data or files (e.g. “move,” “copy,” “import,” “segregate”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    copying or moving files

    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_22/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
     мы
    -1.13
    rões
    -1.05
    เรา
    -1.05
    骓
    -1.02
     by
    -1.02
    这是一个
    -1.02
     unserer
    -1.02
    šė
    -1.01
    пробу
    -0.99
    الع
    -0.95
    POSITIVE LOGITS
     from
    2.14
     to
    1.68
     into
    1.57
     everything
    1.47
     marchio
    1.30
     kaikki
    1.19
    DataTo
    1.13
     comprende
    1.09
     إلى
    1.09
     kafe
    1.09
    Activations Density 0.092%

    No Known Activations