© 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. 64538
    Prev
    Next
    INDEX
    Explanations

    suit your needs

    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
     two
    -1.20
     mainly
    -1.18
    enskap
    -1.16
     it
    -1.08
    blende
    -1.06
     then
    -1.00
    jauh
    -0.97
    endregion
    -0.94
    }}+\
    -0.94
    臍
    -0.92
    POSITIVE LOGITS
     you
    1.16
     подобрать
    1.15
     suit
    1.06
     phù
    1.02
     každé
    0.95
     whatever
    0.94
     trouverez
    0.94
    sedia
    0.93
    自分に
    0.93
    ($(
    0.91
    Activations Density 0.060%

    No Known Activations