© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127544
    Prev
    Next
    INDEX
    Explanations

    German adjective endings / prefixes

    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
    躋
    -2.47
    妡
    -2.41
    --
    -2.34
    ,
    -2.31
    I
    -2.30
    !!!!!!!
    -2.27
    時間
    -2.27
    实力
    -2.27
    虽
    -2.22
    媄
    -2.22
    POSITIVE LOGITS
     черная
    2.83
     ที่
    2.42
     notable
    2.39
    ized
    2.33
    捗
    2.30
     noteworthy
    2.28
    🩻
    2.23
     precise
    2.19
     \
    2.16
    嘁
    2.13
    Activations Density 0.018%

    No Known Activations