© 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. 22533
    Prev
    Next
    INDEX
    Explanations

    list indexing and slicing

    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
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -1.35
    july
    -1.25
    тится
    -1.23
    alpa
    -1.21
     OCTOBER
    -1.19
     Głów
    -1.17
     birlikte
    -1.14
     gier
    -1.13
     Group
    -1.09
     Aufgabe
    -1.09
    POSITIVE LOGITS
     when
    2.06
     because
    1.57
     despite
    1.50
     although
    1.50
     Prevents
    1.49
     even
    1.45
    今後も
    1.45
    批評
    1.38
     WALTZ
    1.38
    支店
    1.38
    Activations Density 0.182%

    No Known Activations