© 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. 98415
    Prev
    Next
    INDEX
    Explanations

    technical terms and foreign languages

    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
     hela
    0.38
    Hz
    0.38
    ኰ
    0.37
     lauded
    0.37
     دوسرا
    0.37
     heralded
    0.37
     unem
    0.37
     kum
    0.37
    ======
    0.37
    லோக
    0.37
    POSITIVE LOGITS
    ំប
    0.47
    μά
    0.40
    getInput
    0.38
    டைந்து
    0.38
    carte
    0.37
    찮
    0.37
    Mé
    0.36
    ברי
    0.35
    冕
    0.35
    感的
    0.35
    Activations Density 1.791%

    No Known Activations