© 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. 38541
    Prev
    Next
    INDEX
    Explanations

    currency exchange rates

    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
     poliéster
    -1.17
    рений
    -1.16
    меров
    -1.16
    Parece
    -1.16
    鬟
    -1.15
    Worked
    -1.14
    itename
    -1.13
     blessure
    -1.13
     about
    -1.12
    ]=="
    -1.12
    POSITIVE LOGITS
    ícias
    1.35
    ଷ
    1.31
    那我
    1.19
     forskjellige
    1.17
    acją
    1.16
    念头
    1.16
    噜
    1.15
     большинстве
    1.14
    ଦ
    1.13
    transaksi
    1.11
    Activations Density 0.066%

    No Known Activations