© 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. 72113
    Prev
    Next
    INDEX
    Explanations

    words starting with Pul

    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
    是他
    -2.41
    ありますが
    -2.31
     But
    -2.27
    馀
    -2.27
     y
    -2.22
    ないと
    -2.20
    墻
    -2.19
    锭
    -2.16
     pueda
    -2.11
    あれば
    -2.11
    POSITIVE LOGITS
    偸
    2.95
    1
    2.94
    tedì
    2.63
    瑨
    2.59
    蟜
    2.58
    ᐡ
    2.58
    汭
    2.58
    蟶
    2.58
    cję
    2.53
    鬭
    2.52
    Activations Density 0.004%

    No Known Activations