© 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. 38453
    Prev
    Next
    INDEX
    Explanations

    regular season

    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
    {
    -2.00
    </h2>
    -1.68
    ⦊
    -1.66
    捋
    -1.64
     colleagues
    -1.63
     começaram
    -1.61
    guantes
    -1.59
    隳
    -1.56
     amplia
    -1.55
    fecture
    -1.55
    POSITIVE LOGITS
    l
    2.28
     for
    2.13
    i
    1.95
    a
    1.91
    最重要的
    1.91
    s
    1.70
    3
    1.68
    es
    1.66
    all
    1.63
    鏨
    1.62
    Activations Density 0.003%

    No Known Activations