© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39840
    Prev
    Next
    INDEX
    Explanations

    country 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
    僦
    -1.02
     Mereka
    -1.01
    ݂
    -1.00
    廰
    -0.97
     that
    -0.97
     cuchara
    -0.96
     прошло
    -0.96
     Olivenöl
    -0.95
     Semua
    -0.94
    ächst
    -0.94
    POSITIVE LOGITS
    ecznie
    0.99
    specifically
    0.98
     laws
    0.97
     where
    0.97
     još
    0.96
    에서
    0.95
     Lum
    0.93
    where
    0.92
     دارای
    0.92
    几人
    0.91
    Activations Density 0.089%

    No Known Activations