© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12508
    Prev
    Next
    INDEX
    Explanations

    `Patient safety`

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

    This neuron detects code syntax elements like semicolons, quotes, brackets, and other programming punctuation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    apropri
    -0.84
     पुर
    -0.80
    |"
    -0.76
     cidade
    -0.75
    orna
    -0.75
    coccal
    -0.75
     lname
    -0.75
    活性
    -0.75
    izarro
    -0.74
    aner
    -0.73
    POSITIVE LOGITS
     लेखक
    0.95
     ditawarkan
    0.93
     its
    0.91
    espère
    0.85
     suffix
    0.84
     tampil
    0.84
    aryng
    0.83
    suffix
    0.81
    jamientos
    0.81
     exacta
    0.80
    Activations Density 0.020%

    No Known Activations