© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4625
    Prev
    Next
    INDEX
    Explanations

    beauty products

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0.70
     ship
    0.59
    IM
    0.58
    City
    0.57
    ه
    0.57
    IA
    0.55
     liaison
    0.55
     trespass
    0.55
    IC
    0.55
    ing
    0.54
    POSITIVE LOGITS
     космети
    1.24
    💄
    1.14
    化妆
    1.09
     Shampoo
    1.08
     Cosmetics
    1.07
     Cosmetic
    1.07
     Hair
    1.06
     HAIR
    1.06
     hairc
    1.05
     Makeup
    1.05
    Activations Density 0.180%

    No Known Activations