© 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. 80046
    Prev
    Next
    INDEX
    Explanations

    reporting factual information

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

    The neuron fires on formal academic or scientific jargon—terms like “research,” “reports,” “discipline,” “initiative,” etc.—marking scholarly or research-oriented language.

    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
     &
    -1.27
    [
    -1.23
    -1.15
    长的
    -1.09
    (
    -1.03
    และ
    -1.00
    同样
    -1.00
    西兰
    -0.97
     to
    -0.95
    遗憾
    -0.95
    POSITIVE LOGITS
     概要
    1.62
    っていきます
    1.58
    取决
    1.40
     メニュー
    1.38
    灕
    1.32
    hướng
    1.27
     sekarang
    1.27
    Ваш
    1.24
     importanza
    1.23
    
    1.23
    Activations Density 0.034%
    No Known Activations