© 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. 65035
    Prev
    Next
    INDEX
    Explanations

    names and non-english suffixes

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

    The neuron flags tokens that are clearly non-English (foreign-language words).

    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
     mystérie
    -1.69
    ’
    -1.59
     Weisheit
    -1.58
     éco
    -1.51
     brasileiros
    -1.51
     irse
    -1.50
    6
    -1.45
    𝘆
    -1.44
     какую
    -1.43
     you
    -1.41
    POSITIVE LOGITS
     permitirá
    1.59
    翾
    1.57
    ʯ
    1.38
     especially
    1.37
     Shoulders
    1.35
     demonstrated
    1.34
     fragmento
    1.34
    🩻
    1.31
     produkty
    1.30
    ತ್ತು
    1.30
    Activations Density 0.031%

    No Known Activations