© 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. 68713
    Prev
    Next
    INDEX
    Explanations

    Rocky Mountain or Rockies related locations

    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
    Ꮉ
    -2.28
     they
    -2.06
    Выводы
    -2.05
    纐
    -1.88
     actúa
    -1.83
     Synag
    -1.80
    泂
    -1.78
    OUTUBE
    -1.76
    实话
    -1.75
     Bedür
    -1.74
    POSITIVE LOGITS
     şi
    2.42
     them
    2.11
     них
    2.02
    ᅫ
    1.98
     și
    1.97
    ～♪
    1.95
     őket
    1.90
     Москва
    1.85
    欧式
    1.84
     verfügb
    1.80
    Activations Density 0.004%

    No Known Activations