© 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. 93673
    Prev
    Next
    INDEX
    Explanations

    DOM node

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

    This neuron detects code tokens referring to DOM Node interfaces and nodeType constants (e.g. ELEMENT_NODE, DOCUMENT_NODE, Node.getNodeType).

    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
     pension
    -1.21
    Martes
    -0.98
     Pension
    -0.96
    Pension
    -0.93
     pensions
    -0.90
    pension
    -0.88
     travaillé
    -0.77
    ējās
    -0.77
    isées
    -0.75
     Pensions
    -0.75
    POSITIVE LOGITS
     node
    1.37
     Node
    1.22
    nodeType
    1.17
    Node
    1.10
     NODE
    1.05
    NodeType
    1.03
    NODE
    1.02
    NodeName
    0.98
     nodes
    0.97
    node
    0.96
    Activations Density 0.017%

    No Known Activations