© 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. 192249
    Prev
    Next
    INDEX
    Explanations

    naming specific items

    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
    bido
    0.44
    是我
    0.41
     가수
    0.39
     రోజుల
    0.39
     ওসমান
    0.37
     prestaciones
    0.37
    ewomen
    0.37
     спорттук
    0.36
     आश
    0.36
    駭
    0.36
    POSITIVE LOGITS
     rejects
    0.38
    メージ
    0.38
     druck
    0.38
    故
    0.38
    ূর্তি
    0.37
     produziert
    0.36
     encrypt
    0.36
    امی
    0.36
     poch
    0.36
     ویر
    0.36
    Activations Density 0.002%

    No Known Activations