© 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. 72513
    Prev
    Next
    INDEX
    Explanations

    Python code and module names

    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
     finally
    -1.31
     detalló
    -1.06
     journalistes
    -1.02
     fuß
    -1.02
     besonder
    -1.02
    OMEN
    -1.01
     ministres
    -1.01
    czeniu
    -1.00
     パス
    -0.99
    どちら
    -0.98
    POSITIVE LOGITS
    ório
    1.06
     \
    1.05
    拢
    1.02
     EXAMPLE
    1.02
     indépendant
    1.00
     échou
    1.00
     Sagan
    0.99
     américa
    0.95
    ұл
    0.94
    昀
    0.94
    Activations Density 0.038%

    No Known Activations