© 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. 6782
    Prev
    Next
    INDEX
    Explanations

    the trevor project

    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
     घ
    0.80
     mas
    0.72
     sil
    0.70
    í
    0.69
     Hou
    0.69
    美
    0.68
     ঘ
    0.66
     sharp
    0.66
     silicate
    0.66
     টিকিট
    0.65
    POSITIVE LOGITS
     म्हणतात
    0.81
    鲲
    0.79
     LGBTQ
    0.78
     Chromebook
    0.76
     étapes
    0.76
    ેશન
    0.73
    はよう
    0.70
    旃
    0.70
     undertakes
    0.69
    تميز
    0.69
    Activations Density 0.059%

    No Known Activations