© 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. 19779
    Prev
    Next
    INDEX
    Explanations

    municipal entities and services

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

    The neuron specifically activates on the word “municipal.”

    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
     protože
    -2.69
    栳
    -2.53
     Of
    -2.53
    
    -2.47
    nambuco
    -2.47
     Германия
    -2.47
    
    -2.38
     immense
    -2.33
     ซึ่ง
    -2.30
     แต่
    -2.23
    POSITIVE LOGITS
    (
    3.84
    m
    3.47
    Following
    3.19
     groundbreaking
    2.78
    Even
    2.72
    1
    2.70
     вечером
    2.66
     burgeoning
    2.64
    There
    2.63
     unrelenting
    2.63
    Activations Density 0.004%

    No Known Activations