© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66340
    Prev
    Next
    INDEX
    Explanations

    Jiang and Chiang prefixes

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

    This neuron detects occurrences of the substring “jiang,” i.e. the token “Jiang” in Chinese names and place names.

    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
    憷
    -2.75
    ᠂
    -2.52
    垕
    -2.52
    趿
    -2.44
    🫃
    -2.41
    ちょこ
    -2.39
    ༀ
    -2.38
     они
    -2.31
    想着
    -2.27
    釕
    -2.25
    POSITIVE LOGITS
     From
    3.03
     After
    2.73
     During
    2.61
    (
    2.56
     On
    2.56
     and
    2.48
     Throughout
    2.45
     Originally
    2.42
     But
    2.41
     Surprisingly
    2.38
    Activations Density 0.003%

    No Known Activations