© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15807
    Prev
    Next
    INDEX
    Explanations

    UI setup in 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
    Not in Any Lists

    No Comments

    Negative Logits
     Staates
    -1.05
     cayó
    -1.03
     Volkes
    -1.00
     murieron
    -0.98
     manutenzione
    -0.97
    pgfmath
    -0.96
     damal
    -0.96
     касается
    -0.96
    ַּ
    -0.96
     to
    -0.95
    POSITIVE LOGITS
     Alc
    1.20
    farben
    1.15
     hôtels
    1.02
     départements
    1.02
     cso
    1.02
     erit
    1.01
     FOTO
    1.00
     instead
    1.00
     CAPIT
    1.00
     principale
    0.99
    Activations Density 0.016%

    No Known Activations