© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85958
    Prev
    Next
    INDEX
    Explanations

    data binding

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

    The neuron is triggered by occurrences of “binding”/“DataBinding” (and related data‐binding terminology) 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_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
    .
    -1.70
    嘞
    -1.66
    adakan
    -1.60
     Той
    -1.58
    fangen
    -1.53
     â
    -1.48
    tersebut
    -1.45
     estekak
    -1.45
     …
    -1.43
     onlyOwner
    -1.42
    POSITIVE LOGITS
    1
    1.88
    壼
    1.74
    你也
    1.59
     respects
    1.53
    ”.
    1.52
    .’”
    1.52
    もう少し
    1.50
    ),”
    1.48
     .”
    1.47
    ...”
    1.46
    Activations Density 0.037%

    No Known Activations