© 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. 26351
    Prev
    Next
    INDEX
    Explanations

    multilingual words and abbreviations

    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
    ₨
    -1.16
     to
    -1.14
    
    -0.99
    iettivo
    -0.99
    šana
    -0.99
    =${
    -0.99
     äta
    -0.99
     seu
    -0.95
    ǀ
    -0.94
     get
    -0.94
    POSITIVE LOGITS
     then
    1.03
    会在
    1.02
     geholfen
    1.01
     bestimm
    1.01
     pesso
    0.96
    ものに
    0.95
     eindeutig
    0.95
     gän
    0.95
     gründ
    0.95
    ihnachten
    0.95
    Activations Density 0.063%

    No Known Activations