© 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. 25152
    Prev
    Next
    INDEX
    Explanations

    language codes and times

    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
     FREDERICK
    -1.04
     any
    -1.04
    閉店
    -1.01
     both
    -1.00
     their
    -0.99
     restoran
    -0.97
    ่วม
    -0.96
    Kaynakça
    -0.96
    声を
    -0.96
     salg
    -0.92
    POSITIVE LOGITS
    <>
    1.14
    也
    1.12
     inférieure
    1.11
     схемы
    1.09
     trám
    1.08
     limão
    1.07
     этих
    1.04
     vying
    1.03
    %">
    1.01
     レッド
    1.00
    Activations Density 0.009%

    No Known Activations