© 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. 16761
    Prev
    Next
    INDEX
    Explanations

    gratitude for help or solutions

    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
    sä
    -1.02
    løs
    -1.02
     häufig
    -1.01
    他们
    -0.99
    我们
    -0.98
    録
    -0.96
     only
    -0.96
    끽
    -0.96
     السلطة
    -0.95
     эффект
    -0.95
    POSITIVE LOGITS
     invaluable
    1.18
     flera
    1.14
     dzięki
    1.13
     dabar
    1.13
     теперь
    1.11
     information
    1.09
     estou
    1.08
    معلومات
    1.07
     now
    1.04
     greatly
    1.03
    Activations Density 0.022%

    No Known Activations