© 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. 114220
    Prev
    Next
    INDEX
    Explanations

    items in square brackets

    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
     and
    -2.27
     abiertas
    -1.97
     has
    -1.91
     increases
    -1.80
     or
    -1.80
     which
    -1.75
    あります
    -1.73
     this
    -1.71
     about
    -1.66
     at
    -1.66
    POSITIVE LOGITS
     ؛
    1.95
     \
    1.92
    撄
    1.89
    ⢪
    1.87
    “
    1.87
    ࿊
    1.87
    PLEASE
    1.86
     [\
    1.85
    苤
    1.82
    几个人
    1.81
    Activations Density 0.070%

    No Known Activations