© 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. 43301
    Prev
    Next
    INDEX
    Explanations

    向, 双向, 导入, 查看

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

    This neuron detects instances of the Chinese preposition “向.”

    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
    瑧
    -2.97
    ⑊
    -2.70
    衚
    -2.41
    ’:
    -2.41
    鱟
    -2.38
     forwarded
    -2.36
    閎
    -2.34
    
    -2.31
    偌
    -2.25
    栝
    -2.22
    POSITIVE LOGITS
    are
    2.83
    or
    2.70
     For
    2.47
     stalwart
    2.39
    It
    2.34
    You
    2.30
     большим
    2.28
     disgruntled
    2.27
     hapless
    2.22
    你們
    2.20
    Activations Density 0.001%

    No Known Activations