© 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-262K
    7. 2942
    Prev
    Next
    INDEX
    Explanations

    Nike, Adidas, ASOS sneakers

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     computable
    0.51
    icherweise
    0.48
     XPath
    0.48
     recursive
    0.47
    ScriptObject
    0.47
     справо
    0.46
     imputation
    0.46
    疡
    0.44
     drowsiness
    0.43
    じん
    0.43
    POSITIVE LOGITS
     Nike
    2.03
     nike
    1.85
    Nike
    1.83
     sneaker
    1.82
     sneakers
    1.80
     Adidas
    1.80
     adidas
    1.73
    Adidas
    1.59
     NIKE
    1.56
    adidas
    1.53
    Activations Density 0.013%

    No Known Activations