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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40322
    Prev
    Next
    INDEX
    Explanations

    specific markers

    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
     of
    -1.30
     JMenuItem
    -1.16
     sâ
    -1.09
     terlaris
    -1.08
     from
    -1.05
     зала
    -1.05
    
    -1.05
     ActionListener
    -1.04
     initComponents
    -1.03
     legen
    -0.99
    POSITIVE LOGITS
     gewiß
    1.08
    outube
    1.03
     alcune
    1.02
     dře
    1.00
     içerisinde
    0.98
    giphy
    0.97
     двигателя
    0.96
     präsenti
    0.95
    nikon
    0.94
     Handeln
    0.94
    Activations Density 0.009%

    No Known Activations