© 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. 16561
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ského
    -1.05
    ScopeManager
    -1.05
    нымъ
    -1.02
    刹那
    -1.02
     pentru
    -1.02
     сейчас
    -1.01
    斧
    -1.00
    ㅿ
    -0.98
     เปิด
    -0.97
    能量
    -0.97
    POSITIVE LOGITS
     these
    1.27
     Nachfrage
    1.19
     theoretically
    1.08
     then
    1.05
     rigorously
    1.05
    Not
    1.04
     easier
    1.02
     immediately
    1.02
     comparing
    1.00
    ＾＾；
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.