© 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. 10-GEMMASCOPE-RES-131K
    4. 110836
    Prev
    Next
    INDEX
    Explanations

    administrative divisions and titles

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

    The neuron fires on mentions of administrative or governmental division terms (e.g. department, county, district, regional).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Galería
    -1.31
     dovr
    -1.26
    诡异
    -1.23
     vada
    -1.20
     udang
    -1.14
     maría
    -1.13
     sekal
    -1.10
    хваты
    -1.09
     cercano
    -1.09
     murale
    -1.09
    POSITIVE LOGITS
    下一篇
    1.27
    ється
    1.23
    ."
    1.18
    umpulkan
    1.13
     similarly
    1.11
     recognizing
    1.02
     berechtigt
    1.02
     organized
    1.01
     recognized
    1.01
     correctamente
    1.00
    Activations Density 0.052%

    No Known Activations