© 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-16K
    7. 7870
    Prev
    Next
    INDEX
    Explanations

    research and academic content

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    秞
    0.43
    Readme
    0.39
     एलि
    0.39
    rbrack
    0.39
    Fechar
    0.38
    ◸
    0.38
     analges
    0.38
     Confederacy
    0.38
     geschikt
    0.38
     consulted
    0.37
    POSITIVE LOGITS
     researches
    0.51
     연구
    0.49
     исследова
    0.47
    研究
    0.46
    연구
    0.46
     nghiên
    0.43
    的研究
    0.43
    㓈
    0.42
     исследования
    0.42
     research
    0.42
    Activations Density 0.036%

    No Known Activations