© 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. 85149
    Prev
    Next
    INDEX
    Explanations

    code blocks or curly braces

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

    The neuron fires on standalone curly‐brace tokens (i.e. the “{” or “}” that mark code‐block 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
    <em>
    -2.41
    氿
    -2.39
    <<<<<<<
    -2.33
    我們
    -2.30
    更
    -2.30
    Let
    -2.22
    isation
    -2.16
    Of
    -2.16
     μια
    -2.13
    ing
    -2.11
    POSITIVE LOGITS
    🫅
    2.78
     retratos
    2.58
    linawan
    2.55
    횃
    2.52
    諴
    2.50
     explicado
    2.34
    arangay
    2.28
    ctores
    2.27
    \&
    2.25
     that
    2.23
    Activations Density 0.004%

    No Known Activations