© 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. 76138
    Prev
    Next
    INDEX
    Explanations

    tree structures

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

    The neuron is highly activated by numeric tokens (i.e. numbers) in the 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
    tería
    -0.89
     arable
    -0.82
    ellus
    -0.73
    Melon
    -0.70
    枚目
    -0.69
    idov
    -0.69
     humer
    -0.69
    creatic
    -0.69
    ƒ
    -0.68
    推荐阅读
    -0.68
    POSITIVE LOGITS
     tree
    2.61
    tree
    2.17
     Tree
    2.05
    Tree
    2.03
     TREE
    1.80
     trees
    1.63
    TreeNode
    1.62
     TreeNode
    1.59
    TREE
    1.58
    树
    1.52
    Activations Density 0.040%

    No Known Activations