© 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. 65459
    Prev
    Next
    INDEX
    Explanations

    child or children

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

    The neuron strongly fires on code tokens that refer to DOM/XML “node” concepts (e.g. Node, ELEMENT_NODE, getNodeType, getChildNodes).

    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
     родителей
    -1.02
     Mom
    -0.95
     madre
    -0.93
    母の
    -0.90
     отец
    -0.90
    Mom
    -0.88
    categories
    -0.87
     мамы
    -0.87
    両親
    -0.87
    жнарод
    -0.86
    POSITIVE LOGITS
     children
    4.16
     child
    3.91
    children
    2.80
    child
    2.72
     daughter
    2.59
    Children
    2.53
    子
    2.52
    Child
    2.48
     Children
    2.44
     kids
    2.41
    Activations Density 0.144%

    No Known Activations