© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64296
    Prev
    Next
    INDEX
    Explanations

    travel mug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    の商品
    -1.06
    bukti
    -1.06
    ならでは
    -1.05
    Aktiv
    -1.04
    今週
    -1.00
    Kontak
    -0.99
     baratas
    -0.99
    Lain
    -0.98
    マジで
    -0.97
    樒
    -0.97
    POSITIVE LOGITS
    mu
    1.09
    ove
    1.02
    ano
    1.02
    d
    1.01
    at
    1.00
    l
    0.99
    ure
    0.96
     مواليد
    0.95
    o
    0.95
    line
    0.94
    Activations Density 0.019%

    No Known Activations