© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    luxury lifestyle and fashion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     skole
    1.37
     เด็ก
    1.23
     주민
    1.21
    町村
    1.17
    Republican
    1.14
     Voter
    1.13
     Legislature
    1.12
     karne
    1.11
    깽
    1.09
     HttpServer
    1.09
    POSITIVE LOGITS
     Cannes
    2.95
     penthouse
    2.89
     luxe
    2.80
     Luxury
    2.75
     ELLE
    2.63
     interiors
    2.62
     Sotheby
    2.61
     Vogue
    2.61
     EMEA
    2.61
    Luxury
    2.59
    Activations Density 0.659%

    No Known Activations