© 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. 34-GEMMASCOPE-RES-131K
    4. 66092
    Prev
    Next
    INDEX
    Explanations

    special characters and code syntax

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

    The neuron fires on isolated code‐syntax delimiters and punctuation (e.g. backticks, braces, angle brackets, slashes, quotes, etc.).

    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
     trzech
    -0.98
     trei
    -0.91
    russia
    -0.89
    {}/
    -0.88
     dwóch
    -0.87
    вшиеся
    -0.86
    rious
    -0.86
    danny
    -0.86
     eight
    -0.85
    偲
    -0.85
    POSITIVE LOGITS
    ○○
    1.19
     %-
    1.15
     \""
    0.99
     vitamine
    0.96
     persil
    0.95
     uſ
    0.94
     kring
    0.93
     valuta
    0.93
     salade
    0.93
     kado
    0.92
    Activations Density 0.043%

    No Known Activations