© 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. 117675
    Prev
    Next
    INDEX
    Explanations

    tree layout syntax and nodes

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

    The neuron is chiefly detecting numeric literals (i.e. sequences of digits) in code or technical text.

    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
     Alfalfa
    -0.81
     alfalfa
    -0.79
    EditorBrowsable
    -0.75
     grassland
    -0.75
     habló
    -0.72
     đoàn
    -0.72
     スキン
    -0.71
     sunflowers
    -0.69
    raktion
    -0.69
     übernehmen
    -0.68
    POSITIVE LOGITS
    Tree
    1.04
     node
    0.97
     tree
    0.97
    node
    0.94
    tree
    0.92
    BinaryTree
    0.91
     Tree
    0.91
    左右
    0.90
     subtree
    0.89
    etree
    0.87
    Activations Density 0.018%

    No Known Activations