© 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. 9802
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by medical terms

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

    punctuation marks, especially periods, at the ends of paragraphs or text sections.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on punctuation symbols (commas, periods, parentheses, semicolons, 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_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
     Akademi
    -1.13
     Kontrol
    -1.13
     dini
    -1.08
     restoran
    -1.07
     Teknik
    -1.07
     surla
    -1.06
    👎
    -1.05
    🍻
    -1.05
     vokal
    -1.05
     deng
    -1.05
    POSITIVE LOGITS
    或者是
    1.19
     then
    0.97
    抜群
    0.95
    もう一度
    0.95
    或者
    0.91
     Erwachsene
    0.90
     Krankheit
    0.89
    に行って
    0.88
     tratan
    0.87
    regation
    0.85
    Activations Density 0.012%

    No Known Activations