© 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. 10-GEMMASCOPE-RES-131K
    7. 84139
    Prev
    Next
    INDEX
    Explanations

    code blocks opening brackets

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

    The neuron fires on code‐style punctuation tokens—parentheses, braces, square brackets, and similar delimiters.

    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
    姈
    -1.71
     Melhor
    -1.69
    釙
    -1.65
    烔
    -1.57
     Trabalho
    -1.56
    けない
    -1.56
     accedi
    -1.54
     dipinto
    -1.52
     卷
    -1.48
    зацию
    -1.48
    POSITIVE LOGITS
     -
    2.06
     [
    1.84
     ...
    1.55
    ...
    1.55
     (
    1.52
    ’
    1.43
    c
    1.43
    !
    1.41
    1
    1.40
     he
    1.38
    Activations Density 0.006%

    No Known Activations