© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74851
    Prev
    Next
    INDEX
    Explanations

    only in e-commerce

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

    The neuron is strongly triggered by Portuguese content—especially academic terms like curso, disciplina, aluno—i.e. it detects Portuguese-language text.

    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
    2
    -1.67
    ´
    -1.66
     después
    -1.64
    '
    -1.61
     жы
    -1.59
     после
    -1.56
    &
    -1.55
    ing
    -1.55
    `
    -1.50
     siempre
    -1.49
    POSITIVE LOGITS
    焢
    1.92
     typy
    1.63
     suche
    1.63
     auta
    1.59
     alugar
    1.59
    borgen
    1.58
     tyme
    1.54
     effets
    1.52
    鲥
    1.52
     nosi
    1.51
    Activations Density 0.168%

    No Known Activations