© 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. 6683
    Prev
    Next
    INDEX
    Explanations

    `sys/` header includes

    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
     obwohl
    -2.75
    ↵
    -2.70
     wobei
    -2.69
     Она
    -2.52
     It
    -2.47
    嗳
    -2.39
     
    -2.39
     showcase
    -2.38
    出入
    -2.34
     In
    -2.30
    POSITIVE LOGITS
    >
    2.92
    s
    2.81
    ㈮
    2.67
    \
    2.64
    ຼ
    2.53
    ㈯
    2.45
     ila
    2.41
     建築
    2.38
     secondi
    2.34
     zoude
    2.31
    Activations Density 0.004%

    No Known Activations