© 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. 98672
    Prev
    Next
    INDEX
    Explanations

    technical programming concepts

    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
     theſe
    -1.46
     will
    -1.41
     thoſe
    -1.34
     for
    -1.30
    atoires
    -1.22
    匾
    -1.22
     następujące
    -1.20
    oczes
    -1.16
     نوع
    -1.15
    TableRow
    -1.14
    POSITIVE LOGITS
    Ayrıca
    1.50
     randonnée
    1.48
    Karakter
    1.43
    ΡΟ
    1.41
     السكان
    1.35
    他們的
    1.35
    Thursday
    1.34
    荣誉
    1.29
     ciudadana
    1.27
    archical
    1.27
    Activations Density 0.172%

    No Known Activations