© 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. 7853
    Prev
    Next
    INDEX
    Explanations

    four

    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
     восем
    0.61
     семь
    0.61
     acht
    0.60
     eight
    0.58
     вось
    0.57
     Eight
    0.55
     oito
    0.54
     ocho
    0.50
    八
    0.50
     seven
    0.50
    POSITIVE LOGITS
    4
    1.43
     forty
    1.38
     Forty
    1.36
     ४
    1.30
    ４
    1.25
    ٤
    1.23
    ⁴
    1.23
     ۴
    1.20
    Forty
    1.19
    𝟰
    1.18
    Activations Density 0.250%

    No Known Activations