© 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. 105955
    Prev
    Next
    INDEX
    Explanations

    foreign language words and phrases

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

    This neuron responds to tokens containing non-ASCII or diacritic characters (i.e. foreign-language words or 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
     is
    -2.44
    I
    -2.23
     votre
    -2.16
    L
    -2.16
    ⚋
    -2.13
     cinq
    -2.05
    都快
    -2.05
     "
    -2.05
    :
    -1.98
    蹰
    -1.98
    POSITIVE LOGITS
    習慣
    1.76
    
    1.73
     that
    1.68
     they
    1.66
     admittedly
    1.63
     菇
    1.63
    ayage
    1.57
     PARTE
    1.55
     BERT
    1.55
    presents
    1.52
    Activations Density 0.001%

    No Known Activations