© 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. 83785
    Prev
    Next
    INDEX
    Explanations

    introductions of context

    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
    ࿆
    -1.96
     LCCN
    -1.95
    %;
    -1.94
    クエ
    -1.94
     '>=
    -1.92
    xnn
    -1.89
     rezept
    -1.88
    艄
    -1.88
    arxiv
    -1.87
     \
    -1.86
    POSITIVE LOGITS
     przyczyn
    1.90
    is
    1.88
    out
    1.77
     problemet
    1.72
    犧
    1.68
    are
    1.67
    u
    1.67
    它们
    1.67
     they
    1.66
     impide
    1.66
    Activations Density 0.002%

    No Known Activations