© 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. 47570
    Prev
    Next
    INDEX
    Explanations

    market sales and farms

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

    This neuron detects mentions of markets—especially outdoor or farmers’ markets.

    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
    ブログ村
    -1.76
     caneca
    -1.73
    两
    -1.46
    ごち
    -1.41
    ホント
    -1.41
    jenost
    -1.38
     frattempo
    -1.38
     maquiagem
    -1.38
     estúdio
    -1.37
     pulseira
    -1.37
    POSITIVE LOGITS
     or
    1.66
    泌
    1.56
    sweetalert
    1.41
    '
    1.36
     ngon
    1.33
    ',
    1.29
    奇妙
    1.28
     Bitte
    1.28
    ████
    1.27
     of
    1.26
    Activations Density 0.011%

    No Known Activations