© 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. 10-GEMMASCOPE-RES-131K
    7. 10230
    Prev
    Next
    INDEX
    Explanations

    dom

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

    The neuron flags code tokens referring to “dom” (e.g. import or usage of a DOM/dom module).

    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
    髏
    -2.73
    öpfer
    -2.69
    '
    -2.64
    what
    -2.58
    There
    -2.56
    Even
    -2.36
    Being
    -2.34
     даже
    -2.34
    vantaged
    -2.30
    With
    -2.28
    POSITIVE LOGITS
    the
    3.48
    i
    3.25
    ৢ
    3.00
    dom
    2.97
    ي
    2.94
    ised
    2.72
    ఽ
    2.72
    튿
    2.69
    enangan
    2.64
    脔
    2.64
    Activations Density 0.006%

    No Known Activations