© 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. 219989
    Prev
    Next
    INDEX
    Explanations

    cooking and measurements

    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
     brave
    0.41
    ěř
    0.41
     FORMAT
    0.37
     dene
    0.37
     Combine
    0.36
    勇
    0.36
    ítě
    0.36
     हिम्मत
    0.36
     cave
    0.36
    клад
    0.36
    POSITIVE LOGITS
    Lifetime
    0.39
    proguard
    0.38
    outs
    0.38
    iggins
    0.38
    ኔታ
    0.37
     والف
    0.37
    seven
    0.37
    Ada
    0.36
    鈍
    0.36
    achev
    0.36
    Activations Density 0.000%

    No Known Activations