© 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. 15586
    Prev
    Next
    INDEX
    Explanations

    financial transactions and announcements

    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
     religieux
    -1.74
     eccl
    -1.59
     प्रोड
    -1.59
    ׇ
    -1.59
    ֩
    -1.58
    itados
    -1.52
    อร่อย
    -1.51
     الجلد
    -1.48
    PUESTA
    -1.46
     дів
    -1.45
    POSITIVE LOGITS
    ּוֹ
    1.98
     uitzicht
    1.78
     volledige
    1.68
    靱
    1.68
    ִּ
    1.67
    ֶּ
    1.59
     from
    1.56
     podrían
    1.50
    靭
    1.48
    וּ
    1.48
    Activations Density 0.209%

    No Known Activations