© 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. 95493
    Prev
    Next
    INDEX
    Explanations

    states, countries, cities, areas

    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
     prohi
    -1.16
     präsenti
    -1.10
     stát
    -1.09
    ׇ
    -1.09
     hígado
    -1.08
     alug
    -1.05
     lança
    -1.01
    шир
    -1.00
    র্ব
    -1.00
     anything
    -0.99
    POSITIVE LOGITS
     selected
    1.95
     select
    1.59
     chosen
    1.48
     wybran
    1.43
     ausgewä
    1.38
    וּ
    1.37
    selected
    1.34
     those
    1.28
     cities
    1.27
    ִּ
    1.27
    Activations Density 0.070%

    No Known Activations