© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9255
    Prev
    Next
    INDEX
    Explanations

    tree path components

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

    The neuron consistently activates on occurrences of the word “tree” (often as part of compound identifiers or technical terms, e.g. tree_size, tree-data, treePanel, treeId).

    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
    ↵
    -2.69
    5
    -2.09
    ︐
    -2.00
    ă
    -1.89
    总是
    -1.88
    Thirty
    -1.86
    d
    -1.86
    们的
    -1.78
    了一个
    -1.76
     "",
    
    -1.76
    POSITIVE LOGITS
    this
    2.34
    ,"
    2.17
     gyerek
    2.08
    </h3>
    2.05
    最重要
    2.00
     város
    1.91
    you
    1.90
     amado
    1.88
    ingtones
    1.88
     atendido
    1.85
    Activations Density 0.020%

    No Known Activations