© 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. 22-GEMMASCOPE-RES-131K
    4. 73759
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

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

    This neuron specializes in spotting programming identifiers and keywords—names of commands, functions, classes, variables, and similar code‐oriented tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     außerdem
    -1.02
     Bereichen
    -0.91
     rejected
    -0.86
     Außerdem
    -0.85
    再加上
    -0.85
    *}[
    -0.85
     ebenso
    -0.81
     other
    -0.81
    footnotes
    -0.81
     Beweg
    -0.80
    POSITIVE LOGITS
     Wikimédia
    1.00
    ԝ
    0.98
    İN
    0.98
     Produits
    0.97
     Spéc
    0.96
    chọn
    0.96
    Istorija
    0.95
     januari
    0.94
     prece
    0.94
     вони
    0.94
    Activations Density 0.031%

    No Known Activations