© 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. 42301
    Prev
    Next
    INDEX
    Explanations

    Durham and associated places

    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
    訁
    -2.89
     можуть
    -2.61
     可以
    -2.59
     сделал
    -2.55
     делает
    -2.50
     faldas
    -2.50
     genannten
    -2.47
     There
    -2.47
    anglais
    -2.44
     モード
    -2.44
    POSITIVE LOGITS
    o
    2.72
    趼
    2.41
    figcaption
    2.39
    龊
    2.36
    ༵
    2.31
    e
    2.25
     samme
    2.17
    .
    2.16
     musik
    2.11
    мя
    2.09
    Activations Density 0.002%

    No Known Activations