© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2257
    Prev
    Next
    INDEX
    Explanations

    clipboard operations

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

    This neuron activates on mentions of the clipboard or clipboard‐related operations in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Suk
    -0.87
    setCenter
    -0.84
    Suk
    -0.76
     Cardoso
    -0.73
     weakly
    -0.71
     Dyson
    -0.71
     Conway
    -0.70
    ophi
    -0.70
    ibos
    -0.70
     Tennessee
    -0.69
    POSITIVE LOGITS
     clipboard
    4.81
     Clipboard
    3.66
    clipboard
    3.64
    Clipboard
    3.39
     clip
    2.77
    clip
    2.53
     Clip
    2.50
    Clip
    2.39
    CLIP
    2.31
     CLIP
    2.11
    Activations Density 0.066%

    No Known Activations