© 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. 8824
    Prev
    Next
    INDEX
    Explanations

    working class people

    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
     sikre
    -1.41
     المنتج
    -1.33
     høre
    -1.27
     bruge
    -1.23
     hjælpe
    -1.23
     verra
    -1.21
     fufficient
    -1.18
    軚
    -1.17
    就开始
    -1.16
    ЭС
    -1.16
    POSITIVE LOGITS
     how
    1.47
     =
    1.21
     структура
    1.16
    ’
    1.16
    当前
    1.14
     protegida
    1.13
    ”,
    1.13
     bagaimana
    1.12
     (
    1.11
     who
    1.10
    Activations Density 0.059%

    No Known Activations