© 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. 59437
    Prev
    Next
    INDEX
    Explanations

    paste actions

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

    The neuron strongly activates on the word “paste” (and its inflected forms like “pasted”).

    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
    ’
    -3.73
    thodoxy
    -2.77
    ic
    -2.70
    r
    -2.70
    ان
    -2.63
     समीक्षाएं
    -2.30
    ים
    -2.25
     dieses
    -2.25
    bebasan
    -2.22
     This
    -2.17
    POSITIVE LOGITS
    ↵
    4.34
    当时的
    2.48
     Когда
    2.47
    遢
    2.44
    時間も
    2.41
    Responding
    2.33
     When
    2.33
    Surprisingly
    2.31
    别人的
    2.16
    对方的
    2.14
    Activations Density 0.004%

    No Known Activations