© 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. 98871
    Prev
    Next
    INDEX
    Explanations

    economy, economical, economically

    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
    檮
    -1.80
    
    -1.70
    ௅
    -1.70
    锨
    -1.64
    erschied
    -1.63
    %);
    -1.59
     tiveram
    -1.57
     requiere
    -1.57
     Mainly
    -1.55
     abject
    -1.53
    POSITIVE LOGITS
     but
    1.72
    呖
    1.67
     doesn
    1.59
    while
    1.59
    You
    1.59
     has
    1.59
    we
    1.58
     while
    1.56
    with
    1.52
     тщательно
    1.52
    Activations Density 0.016%

    No Known Activations