© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    order by clauses

    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
    茈
    -1.43
     イラストレーション
    -1.39
     かわ
    -1.38
    蹚
    -1.38
     severa
    -1.37
    使用了
    -1.36
     ホルダー
    -1.35
    蹋
    -1.34
     quantités
    -1.32
    Ꮨ
    -1.31
    POSITIVE LOGITS
     Some
    1.73
     annual
    1.68
     to
    1.67
     impeccable
    1.59
     occasion
    1.59
     Careful
    1.58
     April
    1.55
    ৢ
    1.54
     at
    1.52
     abundant
    1.48
    Activations Density 0.006%

    No Known Activations