© 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. 22-GEMMASCOPE-RES-131K
    7. 127819
    Prev
    Next
    INDEX
    Explanations

    to [verb]

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    最后由
    -1.55
     for
    -1.53
    詳しくは
    -1.48
    彼らは
    -1.40
    コミュニ
    -1.39
    がありますが
    -1.38
    いましたが
    -1.38
    紆
    -1.36
    謳
    -1.36
    遑
    -1.34
    POSITIVE LOGITS
    ↵↵
    1.79
     ensure
    1.62
    ’
    1.28
    斯
    1.28
    人的
    1.23
    他
    1.16
    ところに
    1.13
     hébergement
    1.13
    =
    1.12
     Umständen
    1.09
    Activations Density 0.026%

    No Known Activations