© 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. 32769
    Prev
    Next
    INDEX
    Explanations

      separators

    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
     Lainnya
    -1.38
     Ostat
    -1.19
     also
    -1.13
    ₆
    -1.07
     Manajemen
    -1.06
     Materiales
    -1.05
     Gdy
    -1.04
     but
    -1.04
     melihat
    -1.03
     Tuttavia
    -1.03
    POSITIVE LOGITS
     Perfor
    1.04
     deuil
    1.00
    ROGEN
    0.98
     creeping
    0.96
     clunky
    0.96
    的脸
    0.96
    ꈍ
    0.96
     چهارم
    0.95
     couverts
    0.94
    侣
    0.94
    Activations Density 0.004%

    No Known Activations