© 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. 15690
    Prev
    Next
    INDEX
    Explanations

    investment banking and M&A advisory

    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
    非常好
    -1.38
     négatif
    -1.27
     recently
    -1.24
     fewer
    -1.23
     searched
    -1.22
     how
    -1.22
     tylko
    -1.21
     unless
    -1.20
     couldn
    -1.19
    只有一
    -1.19
    POSITIVE LOGITS
     bleek
    1.34
    uário
    1.32
     الخم
    1.30
    ilogue
    1.30
    APPLE
    1.30
     alphabet
    1.29
    тю
    1.27
    patra
    1.24
    📏
    1.23
    suke
    1.22
    Activations Density 0.018%

    No Known Activations