© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104341
    Prev
    Next
    INDEX
    Explanations

    quantifiers + categories

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

    This neuron detects Chinese quantifier words that express amount or scope (e.g. “任何,” “很多,” “更多,” “所有,” “大量,” “部分”).

    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
            
    -2.80
    }$
    -2.73
    埽
    -2.55
    '
    -2.44
    蛲
    -2.38
    毉
    -2.34
    蠖
    -2.31
     decidedly
    -2.30
     they
    -2.25
     devuelve
    -2.25
    POSITIVE LOGITS
    ဴ
    3.23
    ⛦
    2.94
    ஂ
    2.80
    磲
    2.73
     läsa
    2.72
    Уважа
    2.72
    瑧
    2.66
     besö
    2.64
     스톡
    2.64
     級
    2.58
    Activations Density 0.001%

    No Known Activations