© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6625
    Prev
    Next
    INDEX
    Explanations

    page completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    mitz
    0.82
     Mits
    0.82
    Mits
    0.76
     barium
    0.75
     मेटा
    0.75
     Arduino
    0.73
     certificado
    0.73
    蘸
    0.73
    anco
    0.71
     TRIGGER
    0.71
    POSITIVE LOGITS
     page
    2.33
    page
    2.18
     pages
    2.08
     Page
    2.07
    Page
    2.04
    pages
    1.90
     Pages
    1.90
    页面
    1.80
    Pages
    1.77
     página
    1.76
    Activations Density 0.267%

    No Known Activations