© 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. 34-GEMMASCOPE-RES-131K
    7. 62650
    Prev
    Next
    INDEX
    Explanations

    before or after

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     thêm
    -1.00
    seen
    -0.97
    many
    -0.93
     nuances
    -0.92
    見た目
    -0.91
     tiveram
    -0.91
    わからない
    -0.91
    Seen
    -0.90
    requires
    -0.89
     Allows
    -0.87
    POSITIVE LOGITS
     each
    1.28
     or
    1.22
     and
    1.10
     every
    1.00
     EVERY
    0.99
    åt
    0.96
     leaving
    0.96
     chaque
    0.95
    每个
    0.94
     after
    0.94
    Activations Density 0.054%

    No Known Activations