© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78715
    Prev
    Next
    INDEX
    Explanations

    server nodes and clusters

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

    This neuron responds to numeric specifications of compute resources—especially numbers naming or counting cluster nodes.

    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
    Vezi
    -0.82
    觎
    -0.81
    DebuggerStep
    -0.77
    empresa
    -0.77
    nextProps
    -0.77
    ceau
    -0.75
    团队
    -0.73
    missie
    -0.71
    pektrum
    -0.71
    ritas
    -0.71
    POSITIVE LOGITS
     node
    2.48
     nodes
    2.41
    节点
    1.91
    node
    1.84
    Node
    1.78
     Node
    1.74
    getNode
    1.71
     Nodes
    1.69
    nodes
    1.65
     machines
    1.63
    Activations Density 0.110%

    No Known Activations