© 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. 13420
    Prev
    Next
    INDEX
    Explanations

    specific 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
     rudimentary
    -0.91
    pernicus
    -0.87
     aureus
    -0.87
     with
    -0.86
     There
    -0.84
    ;
    -0.83
    tembro
    -0.82
     slä
    -0.81
     quaint
    -0.79
     еле
    -0.79
    POSITIVE LOGITS
     assiste
    1.09
     sampel
    0.99
     interessa
    0.97
     exé
    0.96
     dominar
    0.93
     UMKM
    0.91
     chłod
    0.90
     aumentando
    0.90
    вится
    0.90
     bénéficient
    0.89
    Activations Density 0.044%

    No Known Activations