© 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. 73727
    Prev
    Next
    INDEX
    Explanations

    government and agency bodies

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

    The neuron is highly sensitive to mentions of formal institutions and government bodies (e.g., official committee names, agencies, and organizational titles).

    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
    ׇ
    -1.70
     молока
    -1.66
     сайті
    -1.56
     ویتامین
    -1.52
     الجلد
    -1.43
     الشاشة
    -1.43
     блюдо
    -1.39
    ֺ
    -1.38
     сыром
    -1.35
     deslig
    -1.34
    POSITIVE LOGITS
    ּוֹ
    1.64
    ִּ
    1.59
     الحكومة
    1.52
     وزار
    1.52
     السياس
    1.34
     правительства
    1.30
    effectiveness
    1.28
     departments
    1.27
     department
    1.26
    erobic
    1.21
    Activations Density 0.059%

    No Known Activations