© 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. 127492
    Prev
    Next
    INDEX
    Explanations

    non-english characters and phrases

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

    This neuron detects tokens containing extended Unicode letters—especially romanized Asian words with diacritics (e.g. pinyin tone marks) or non-ASCII characters.

    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
     sentada
    -1.60
     rústica
    -1.59
     каждом
    -1.56
     afectada
    -1.55
     cortada
    -1.50
     aumentado
    -1.48
     cilindros
    -1.45
     acondicion
    -1.45
     aussehen
    -1.43
    Зага
    -1.42
    POSITIVE LOGITS
     they
    1.83
     —
    1.70
     we
    1.46
     será
    1.41
     Of
    1.36
    atie
    1.33
     is
    1.22
    itisation
    1.22
     frau
    1.22
     tien
    1.21
    Activations Density 0.018%

    No Known Activations