© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48732
    Prev
    Next
    INDEX
    Explanations

    code and parameters like `d=`

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Пер
    0.49
    Про
    0.48
    шкина
    0.47
    はじ
    0.46
    א
    0.46
    됐다
    0.45
    图
    0.45
    ীর
    0.45
    賚
    0.45
    ειας
    0.44
    POSITIVE LOGITS
     building
    0.45
     అంటే
    0.45
     more
    0.44
     else
    0.44
    autres
    0.44
     nearby
    0.43
     other
    0.40
     republican
    0.40
     some
    0.40
     disfr
    0.40
    Activations Density 0.002%

    No Known Activations