© 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. 15694
    Prev
    Next
    INDEX
    Explanations

    n for quantity or count

    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
     “[
    -1.72
    葙
    -1.55
    過ごす
    -1.52
    …”
    -1.50
     “…
    -1.48
     不能
    -1.47
    点は
    -1.43
     perut
    -1.41
     pesso
    -1.38
     convaincre
    -1.36
    POSITIVE LOGITS
    "
    2.11
    ],
    1.47
     gewerb
    1.45
     visuelle
    1.45
    其他
    1.43
    \_
    1.43
     других
    1.43
    lería
    1.43
    人都
    1.42
     ambayo
    1.41
    Activations Density 0.062%

    No Known Activations