© 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. 111304
    Prev
    Next
    INDEX
    Explanations

    part of

    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
     если
    -1.96
     так
    -1.63
     после
    -1.62
     menurun
    -1.62
     ganzes
    -1.55
     уже
    -1.53
     privadas
    -1.52
    。”
    -1.52
    現在
    -1.50
     каждый
    -1.50
    POSITIVE LOGITS
    2
    1.64
    usions
    1.63
    Выводы
    1.56
    攙
    1.55
     éx
    1.52
    やっぱ
    1.52
    Вывод
    1.51
     чёр
    1.51
    lette
    1.48
    的吗
    1.47
    Activations Density 0.009%

    No Known Activations