© 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. 22-GEMMASCOPE-RES-131K
    7. 16672
    Prev
    Next
    INDEX
    Explanations

    date and time fields

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -1.23
     if
    -0.96
    J
    -0.94
     then
    -0.92
     with
    -0.91
     его
    -0.91
    pelle
    -0.88
     is
    -0.88
     for
    -0.86
     jego
    -0.85
    POSITIVE LOGITS
     timestamp
    1.27
     DateTime
    1.18
    ETIME
    1.13
     time
    1.10
    timestamp
    1.09
     kapan
    1.06
    1.05
    1.04
    kező
    1.03
     profesora
    1.03
    Activations Density 0.020%

    No Known Activations