© 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. 6870
    Prev
    Next
    INDEX
    Explanations

    room, camera, or change noun

    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
    -
    -1.60
    郸
    -1.53
    ли
    -1.52
    隨著
    -1.49
     Herausforderung
    -1.47
    ється
    -1.44
    </sup>
    -1.41
    ჻
    -1.41
    okkal
    -1.41
     decoración
    -1.40
    POSITIVE LOGITS
    其它
    1.64
     other
    1.61
    我又
    1.52
    Другие
    1.48
    GORITH
    1.46
     causes
    1.46
    讴
    1.46
     özellikleri
    1.46
     cathédrale
    1.45
    拓展
    1.45
    Activations Density 0.067%

    No Known Activations