© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102699
    Prev
    Next
    INDEX
    Explanations

    Japanese verb endings

    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
     et
    -2.88
    ’
    -2.66
    ar
    -2.36
    ad
    -2.25
     &
    -2.25
    te
    -2.16
    \
    -2.14
     trong
    -2.13
    ts
    -2.11
    ik
    -2.06
    POSITIVE LOGITS
    they
    3.03
    欵
    2.63
     kumaş
    2.45
    ulite
    2.34
    灕
    2.31
     lhes
    2.30
    Sekarang
    2.27
    睺
    2.25
    Hanya
    2.23
    هو
    2.22
    Activations Density 0.002%

    No Known Activations