© 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. 112104
    Prev
    Next
    INDEX
    Explanations

    Chinese culture and names

    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
     our
    -1.39
     each
    -1.27
    autoreleasepool
    -1.16
     another
    -1.09
    UnusedPrivate
    -1.09
    vidades
    -1.05
    ικα
    -1.05
    𝘃
    -1.05
    ogh
    -1.03
    れません
    -1.02
    POSITIVE LOGITS
     demais
    1.31
     mères
    1.14
     क्यों
    1.11
    ження
    1.10
     вони
    1.04
     églises
    1.01
    arrings
    1.01
     demás
    1.00
    uchtung
    1.00
     tatsächlich
    0.99
    Activations Density 0.469%

    No Known Activations