© 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. 45500
    Prev
    Next
    INDEX
    Explanations

    words starting with dist

    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
    呖
    -2.94
    夘
    -2.52
     haupts
    -2.45
    蓐
    -2.31
    緜
    -2.30
     häufigsten
    -2.28
    灕
    -2.28
     funcionalidades
    -2.28
    螓
    -2.27
    溦
    -2.23
    POSITIVE LOGITS
    \
    4.47
    ti
    2.98
    at
    2.83
    ...
    2.81
    ),
    2.77
     '';
    2.58
     {
    2.48
    $,
    2.41
    {
    2.39
     '
    2.31
    Activations Density 0.036%

    No Known Activations