© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 44719
    Prev
    Next
    INDEX
    Explanations

    lazy loading or on-demand loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ِمض
    0.42
    काउंट
    0.41
     subscribing
    0.41
    จำเป็น
    0.40
    ဝန်
    0.39
    ฮ
    0.39
     hjæl
    0.38
    Điều
    0.38
    维生素
    0.38
    दृश्य
    0.37
    POSITIVE LOGITS
     ವಿಧಾನಸಭಾ
    0.44
    就會
    0.43
     خواهد
    0.41
    筱
    0.41
     hijos
    0.39
     Pte
    0.39
     idam
    0.39
     Sdn
    0.38
     dhan
    0.38
    ناء
    0.38
    Activations Density 0.003%

    No Known Activations