© 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. 73743
    Prev
    Next
    INDEX
    Explanations

    Q, Eureka!, customize, question/code

    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
     estação
    -1.03
     seguras
    -1.02
     Flüssigkeit
    -1.01
     Independencia
    -0.97
    Vaata
    -0.96
     send
    -0.95
    allclose
    -0.92
     המ
    -0.90
     июля
    -0.89
     vrienden
    -0.89
    POSITIVE LOGITS
     forestal
    0.97
    wüns
    0.96
     языка
    0.95
     contenuto
    0.93
    Merhaba
    0.92
     매우
    0.91
     specif
    0.90
    注意事
    0.88
     borbo
    0.87
     immense
    0.86
    Activations Density 0.001%

    No Known Activations