© 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. 15642
    Prev
    Next
    INDEX
    Explanations

    military exercises and drills

    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
    Negative Logits
     Dijo
    -1.52
     zowel
    -1.41
    ⅝
    -1.33
     \
    -1.31
    Ĝ
    -1.28
    ﴿
    -1.28
    ائے
    -1.27
     Allí
    -1.27
    了一会儿
    -1.27
     Empieza
    -1.26
    POSITIVE LOGITS
     Виктор
    1.36
    8
    1.35
     brauchen
    1.29
     своих
    1.26
    on
    1.26
    7
    1.19
    ↵↵
    1.18
    嗱
    1.16
     assure
    1.16
    就知道
    1.16
    Activations Density 0.022%

    No Known Activations