© 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-65K
    7. 47613
    Prev
    Next
    INDEX
    Explanations

    section or roman numeral identifier

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    sor
    0.37
    delay
    0.36
    forecast
    0.35
     zufrieden
    0.35
    celli
    0.35
    Tue
    0.34
    দেশের
    0.34
    嬷
    0.34
    vap
    0.33
     pab
    0.33
    POSITIVE LOGITS
     §
    0.65
     Section
    0.65
     SECTION
    0.64
     III
    0.63
     Appendix
    0.63
     section
    0.62
    Section
    0.61
     VII
    0.60
     subsection
    0.59
     VIII
    0.57
    Activations Density 0.027%

    No Known Activations