© 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. 59956
    Prev
    Next
    INDEX
    Explanations

    common actions

    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
     that
    -1.67
     is
    -1.52
    也将
    -1.43
     arbeitete
    -1.38
     bibliothèque
    -1.34
     begle
    -1.28
     gehörte
    -1.28
     beschäf
    -1.28
     spielte
    -1.27
    “
    -1.24
    POSITIVE LOGITS
    They
    1.49
     in
    1.43
    ркут
    1.38
    不然
    1.29
     [])
    1.26
    Применение
    1.24
    Then
    1.23
     of
    1.23
    スポンサーリンク
    1.21
    Suka
    1.20
    Activations Density 0.031%

    No Known Activations