© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40958
    Prev
    Next
    INDEX
    Explanations

    household cleaning and personal care 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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     complicated
    0.39
     attending
    0.39
     tails
    0.38
     wings
    0.38
     role
    0.37
     Parliamentary
    0.37
     அடிப்பட
    0.36
     温
    0.36
     proclamation
    0.35
    历史
    0.35
    POSITIVE LOGITS
     shampoos
    1.54
     toothpaste
    1.53
     shampoo
    1.52
     cosmetics
    1.50
     detergents
    1.47
     detergent
    1.45
     soaps
    1.36
    toothpaste
    1.34
     toiletries
    1.30
     Shampoo
    1.28
    Activations Density 0.020%

    No Known Activations