© 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. 16526
    Prev
    Next
    INDEX
    Explanations

    roles and technical terms

    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
    regarding
    -1.18
    こっち
    -1.03
    ステンレス
    -1.00
     Rosé
    -0.97
    トヨタ
    -0.96
     fibrillation
    -0.95
    ___________
    -0.94
     APPLE
    -0.94
     Passat
    -0.93
     Futsal
    -0.93
    POSITIVE LOGITS
     after
    1.13
    tadır
    1.08
     commercially
    1.06
    لفة
    1.06
     Brüder
    1.05
    unikasi
    1.04
    IMENTS
    1.04
     शुर
    1.02
    privateKey
    1.02
     shortly
    1.01
    Activations Density 0.182%

    No Known Activations