© 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. 22-GEMMASCOPE-RES-131K
    7. 130732
    Prev
    Next
    INDEX
    Explanations

    This neuron detects Go struct field tags (the backtick-enclosed `json:"…"`) in source code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    multilanguage context markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     групи
    -1.05
    вят
    -0.97
     çocu
    -0.95
     ír
    -0.94
     árboles
    -0.94
     komór
    -0.92
    КТ
    -0.92
     espectadores
    -0.91
    ică
    -0.90
    ṯ
    -0.90
    POSITIVE LOGITS
     diejenigen
    1.00
    摂取
    0.87
     jemanden
    0.86
     phổ
    0.82
     있으며
    0.82
     devoted
    0.82
     Deinen
    0.80
    is
    0.80
    没关系
    0.80
     sfera
    0.79
    Activations Density 0.076%

    No Known Activations