© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10555
    Prev
    Next
    INDEX
    Explanations

    market square

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

    The neuron strongly activates on occurrences of the word “market” (including compound forms like “Market Hall,” “market square,” etc.), effectively detecting references to marketplaces.

    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
    泐
    -2.14
    Ꮴ
    -1.91
    岨
    -1.74
     vermag
    -1.70
    ଢ
    -1.67
    鹇
    -1.59
    𓆏
    -1.59
    媄
    -1.58
    的在
    -1.58
    主催
    -1.58
    POSITIVE LOGITS
    '
    2.05
     markets
    1.71
    木材
    1.67
    
    1.60
    教堂
    1.59
     otras
    1.54
    瀲
    1.52
     catchment
    1.50
     mismo
    1.50
    ASUS
    1.49
    Activations Density 0.020%

    No Known Activations