© 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. 43511
    Prev
    Next
    INDEX
    Explanations

    Node.js programming context

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

    The neuron fires on occurrences of “node,” i.e. references to the Node.js runtime.

    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
    .”
    -1.76
     that
    -1.72
     they
    -1.65
     for
    -1.57
     said
    -1.51
     until
    -1.51
     anche
    -1.48
     йыл
    -1.47
     kayna
    -1.45
     que
    -1.44
    POSITIVE LOGITS
    {
    1.77
     Theres
    1.59
     Während
    1.49
    </b>
    1.48
    ка
    1.47
    1
    1.45
     berücksichtigt
    1.45
    ра
    1.45
    ITÀ
    1.41
    Reduce
    1.40
    Activations Density 0.019%

    No Known Activations