© 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. 15613
    Prev
    Next
    INDEX
    Explanations

    "csv", "file", "tensorflow"

    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
     now
    -1.70
     oculta
    -1.50
    PostExecute
    -1.38
    "),
    -1.38
    二百
    -1.35
     it
    -1.34
     ロゴ
    -1.34
    </i>
    -1.30
    <>());
    -1.29
    LEncoder
    -1.27
    POSITIVE LOGITS
     "
    1.41
    hejiang
    1.39
    Ꮴ
    1.37
    mittag
    1.36
     kyllä
    1.34
     apparaissent
    1.31
    Hozzá
    1.30
     Ensure
    1.25
    很多人
    1.24
     one
    1.23
    Activations Density 0.107%

    No Known Activations