© 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. 22-GEMMASCOPE-RES-131K
    7. 32674
    Prev
    Next
    INDEX
    Explanations

    suspected armed militants and soldiers

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ۱۵
    -1.21
     ۱۶
    -1.17
    netinet
    -1.16
    Ингредиенты
    -1.10
     idyllic
    -1.07
     picante
    -1.05
    Algemeen
    -1.05
     спек
    -1.04
    恚
    -1.03
     liksom
    -1.02
    POSITIVE LOGITS
     damaligen
    1.08
    qed
    1.01
    使用
    0.98
    lamydia
    0.98
     belonging
    0.97
     funcionario
    0.93
     sogenannten
    0.90
    🚰
    0.89
    ַּ
    0.88
     using
    0.87
    Activations Density 0.049%

    No Known Activations