© 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. 12516
    Prev
    Next
    INDEX
    Explanations

    scent and fragrance

    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
    Taste
    0.48
    taste
    0.44
     tastes
    0.42
    Raster
    0.42
     taste
    0.41
    口感
    0.40
    მასრულ
    0.38
    钳
    0.38
     हितों
    0.37
    textAppearance
    0.37
    POSITIVE LOGITS
     perfume
    1.36
     fragrance
    1.26
     perfumes
    1.26
     parfum
    1.23
     fragrances
    1.17
     scent
    1.15
    香
    1.06
     perf
    1.05
     scents
    1.05
     Parfum
    1.05
    Activations Density 0.116%

    No Known Activations