© 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. 68573
    Prev
    Next
    INDEX
    Explanations

    cleft lip palate, Bridlington, Siena, Byrd

    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
    In
    -2.84
     he
    -2.64
    榈
    -2.52
     Completely
    -2.47
    櫚
    -2.42
     Surprisingly
    -2.33
    ありました
    -2.31
     Very
    -2.28
     enchanted
    -2.28
     what
    -2.25
    POSITIVE LOGITS
    i
    2.88
    ㈰
    2.73
    *
    2.53
    狁
    2.50
    蚡
    2.47
    푏
    2.44
     scopo
    2.41
     они
    2.41
    ⑊
    2.41
    ?
    2.39
    Activations Density 0.004%

    No Known Activations