© 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. 64379
    Prev
    Next
    INDEX
    Explanations

    legal citations and dates

    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
     is
    -1.22
     basically
    -1.16
     only
    -1.16
    」,
    -1.15
     proste
    -1.11
     мужские
    -1.10
     рады
    -1.10
     assembling
    -1.10
     vitt
    -1.08
     just
    -1.07
    POSITIVE LOGITS
    SEGUIR
    1.04
     Поэтому
    1.02
    other
    1.01
     attribué
    1.00
     :).
    0.99
     jährlich
    0.98
     schuldig
    0.97
     рецепта
    0.97
    こんなに
    0.96
    其余
    0.96
    Activations Density 0.629%

    No Known Activations