© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100357
    Prev
    Next
    INDEX
    Explanations

    foreign and common words with punctuation

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

    This neuron activates on non-English (foreign-language) tokens, especially fragments containing diacritics or other 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
    谖
    -2.03
    puede
    -1.88
     perſon
    -1.85
    
    -1.84
    ⚫
    -1.79
     adresu
    -1.77
     ſou
    -1.77
     purpoſe
    -1.74
    "¿
    -1.73
     kellett
    -1.73
    POSITIVE LOGITS
    ).
    2.19
    <i>
    1.98
     “
    1.88
    The
    1.81
     [
    1.74
     It
    1.71
     jedną
    1.69
     In
    1.67
     them
    1.66
     verheir
    1.63
    Activations Density 0.000%

    No Known Activations