© 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. 38524
    Prev
    Next
    INDEX
    Explanations

    variables and placeholders

    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
     of
    -1.70
     no
    -1.52
     by
    -1.46
     to
    -1.45
     ebenfalls
    -1.27
    ciuto
    -1.27
     your
    -1.23
    もちろん
    -1.22
     además
    -1.20
     \
    -1.19
    POSITIVE LOGITS
     göm
    1.64
    '
    1.50
     yüzük
    1.43
     forbin
    1.42
     detalj
    1.41
     varmt
    1.39
     elbise
    1.38
     schuhe
    1.32
     jongen
    1.30
     gedrag
    1.29
    Activations Density 0.050%

    No Known Activations