© 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. 99028
    Prev
    Next
    INDEX
    Explanations

    words starting with Ass

    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
    Not in Any Lists

    No Comments

    Negative Logits
    太多的
    -3.00
    自身的
    -2.88
    ではまた
    -2.66
    又不
    -2.61
    多年的
    -2.59
    诹
    -2.58
     smacked
    -2.55
     rattled
    -2.50
     ребёнка
    -2.44
    摁
    -2.44
    POSITIVE LOGITS
    还
    2.44
    ↵
    2.44
    ⢌
    2.41
    据说
    2.33
    s
    2.31
    鱘
    2.28
    l
    2.27
     soothe
    2.20
    人の
    2.16
    既然
    2.16
    Activations Density 0.014%

    No Known Activations