© 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. 11252
    Prev
    Next
    INDEX
    Explanations

    multilingual code and tech discussions

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

    the Portuguese word "muito" (meaning "very" or "much").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on Portuguese (and similar Romance‐language) degree or quantity adverbs—words like “muito,” “muitas,” “bastante,” and “mais.”

    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
    ing
    -3.55
    鱨
    -3.20
    蟊
    -2.84
    櫺
    -2.73
    拶
    -2.64
    镦
    -2.58
    𖥦
    -2.56
    an
    -2.56
    謦
    -2.44
    ة
    -2.41
    POSITIVE LOGITS
    м
    2.66
     طریق
    2.19
     использование
    2.16
    鱈
    2.13
    ↵
    2.13
    可能な
    2.11
     of
    2.09
    !)
    2.05
    ський
    2.02
    Ꮟ
    1.97
    Activations Density 0.001%

    No Known Activations