© 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. 22-GEMMASCOPE-RES-131K
    7. 54525
    Prev
    Next
    INDEX
    Explanations

    listing or choices

    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_22/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
    quilo
    -1.62
     广告
    -1.29
    itamos
    -1.27
     绘画
    -1.27
     背包
    -1.26
     经典
    -1.23
    慢慢的
    -1.22
     limpar
    -1.21
    ומים
    -1.20
    Pozdrawiam
    -1.17
    POSITIVE LOGITS
     or
    2.56
     if
    1.68
    或
    1.43
     или
    1.41
     alebo
    1.38
     السياس
    1.34
     либо
    1.23
     this
    1.22
    หรือ
    1.22
     یا
    1.19
    Activations Density 0.009%

    No Known Activations