© 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. 75508
    Prev
    Next
    INDEX
    Explanations

    paths and ways

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    -2.00
     diseñados
    -1.71
     volledige
    -1.62
     podían
    -1.60
     detalladas
    -1.57
     voldoende
    -1.52
     belangrijke
    -1.50
    ）」
    -1.48
     personalizadas
    -1.47
     帽子
    -1.47
    POSITIVE LOGITS
    na
    1.75
    Твор
    1.75
    os
    1.70
     сторон
    1.69
     to
    1.63
     However
    1.63
     Also
    1.60
    vet
    1.56
     samh
    1.55
     Again
    1.54
    Activations Density 0.006%

    No Known Activations