© 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. 78
    Prev
    Next
    INDEX
    Explanations

    Academy of Sciences

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

    academic journal and scientific institution names, particularly abbreviations like "NAS" (National Academy of Sciences) and "Acad. Sci."

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

    The neuron fires strongly on short, capitalized journal or publication-name fragments (e.g. “Acad,” “Sci,” “NAS,” “Trans,” etc.) in citation headers.

    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
    歩道
    -1.19
    forChild
    -1.17
    市的
    -1.16
    ׇ
    -1.12
    道歉
    -1.10
    隧
    -1.09
    𖤣
    -1.09
    神器
    -1.08
     motocicleta
    -1.05
    目前的
    -1.05
    POSITIVE LOGITS
    ↵↵
    1.17
    льних
    1.05
    想
    1.03
     美しい
    1.01
    ヘア
    1.01
    坚定
    0.99
     décès
    0.96
    нием
    0.95
     アメリカ
    0.93
     genoux
    0.93
    Activations Density 0.001%

    No Known Activations