© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30183
    Prev
    Next
    INDEX
    Explanations

    class, explanation, vibe, exploration, mission, extraction

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ธรรม
    0.46
     правильно
    0.45
     предше
    0.45
     restantes
    0.45
    ジュアル
    0.44
    ള്‍
    0.42
    ズル
    0.41
    不斷
    0.41
    ْل
    0.41
     variously
    0.40
    POSITIVE LOGITS
     altogether
    1.59
     Altogether
    1.05
     entirely
    1.04
     than
    0.86
     zupeł
    0.74
     전혀
    0.71
     совсем
    0.70
    全く
    0.70
     niż
    0.68
     geheel
    0.68
    Activations Density 0.001%

    No Known Activations