© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130049
    Prev
    Next
    INDEX
    Explanations

    different languages/scripts

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Annot
    0.43
     Md
    0.43
    VERSION
    0.41
     समा
    0.40
    MD
    0.40
    ynchus
    0.40
    Mot
    0.39
    ס
    0.38
     elim
    0.38
    ASA
    0.38
    POSITIVE LOGITS
    គេ
    0.40
     violent
    0.39
     кто
    0.38
     kids
    0.38
     kinderen
    0.38
    laat
    0.38
     insistent
    0.38
     તમને
    0.38
     duduk
    0.38
     էր
    0.38
    Activations Density 0.001%

    No Known Activations