© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101352
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -1.66
    なぜか
    -1.63
    ようになった
    -1.59
     ayakkabı
    -1.53
     seguirá
    -1.52
    獗
    -1.45
     męski
    -1.40
    Beskrivelse
    -1.38
     améli
    -1.37
     permiten
    -1.34
    POSITIVE LOGITS
    。
    1.93
     of
    1.72
     on
    1.65
     to
    1.56
    bbero
    1.46
     aire
    1.41
     que
    1.39
    .
    1.37
     альбо
    1.34
     электро
    1.33
    Activations Density 0.004%

    No Known Activations