© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8341
    Prev
    Next
    INDEX
    Explanations

    models and miniatures

    np_acts-logits-general · gemini-2.5-flash-lite

    miniature models and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     empower
    0.41
    笼
    0.38
    睞
    0.38
     исполни
    0.37
    妇女
    0.37
    ębior
    0.37
     العلا
    0.37
    琮
    0.37
     empowering
    0.37
    绩效
    0.37
    POSITIVE LOGITS
     styrene
    0.98
    模型
    0.97
     模型
    0.95
     decals
    0.94
    模型的
    0.92
     modeller
    0.91
     miniatures
    0.89
    的模型
    0.84
     miniature
    0.84
     modelling
    0.84
    Activations Density 0.167%

    No Known Activations