© 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. 22651
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     новом
    -1.62
     also
    -1.47
    璟
    -1.41
     будущем
    -1.38
     gier
    -1.35
     aislamiento
    -1.32
     inoltre
    -1.30
    娣
    -1.30
     drenaje
    -1.30
     dalamnya
    -1.29
    POSITIVE LOGITS
    คุณ
    1.40
    많
    1.40
    ल
    1.33
     сейчас
    1.31
    現在
    1.31
    现在
    1.28
    ถ้า
    1.28
    Сейчас
    1.27
    เพราะ
    1.23
    ご覧ください
    1.22
    Activations Density 0.086%

    No Known Activations