© 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. 98894
    Prev
    Next
    INDEX
    Explanations

    data types and code structures

    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
     have
    -2.75
    骘
    -2.39
    俁
    -2.34
    ⅅ
    -2.31
    倧
    -2.31
    Nutrient
    -2.30
    庹
    -2.30
    rainian
    -2.30
     saque
    -2.27
     ProtoMessage
    -2.23
    POSITIVE LOGITS
    &
    3.27
    5
    3.11
    {
    3.11
    4
    2.92
    j
    2.92
     &
    2.89
    \
    2.86
    is
    2.83
    >
    2.81
    --
    2.77
    Activations Density 0.000%

    No Known Activations