© 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. 68499
    Prev
    Next
    INDEX
    Explanations

    starts with tu

    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
    寕
    -3.69
    镦
    -3.52
    拶
    -2.89
    囖
    -2.86
     detención
    -2.70
    ዒ
    -2.66
    IVING
    -2.53
    تیجه
    -2.50
    其妙
    -2.48
    存于
    -2.47
    POSITIVE LOGITS
    section
    3.56
    h
    3.09
    tu
    2.91
    翃
    2.88
    (
    2.61
    l
    2.53
    )
    2.48
    1
    2.47
    缡
    2.45
    秝
    2.41
    Activations Density 0.013%

    No Known Activations