© 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. 10-GEMMASCOPE-RES-131K
    7. 72227
    Prev
    Next
    INDEX
    Explanations

    Kurdistan Region

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ツリー
    -3.31
    1
    -2.73
    '
    -2.66
     gegangen
    -2.64
     stück
    -2.42
     Monfieur
    -2.34
     köln
    -2.31
     zustand
    -2.27
     männer
    -2.25
     resembling
    -2.23
    POSITIVE LOGITS
     здесь
    2.77
    鶿
    2.77
     punishing
    2.70
     seperti
    2.66
     ۱۵
    2.66
    v
    2.56
     ۵
    2.55
     What
    2.53
    晳
    2.53
     hır
    2.50
    Activations Density 0.043%

    No Known Activations