© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 979
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Szeged
    1.15
     ময়মনসিংহ
    1.14
     Arran
    0.98
    Alf
    0.94
     Kampung
    0.93
     شیخ
    0.91
     Larn
    0.91
    ⊿
    0.91
     Lombok
    0.90
    骠
    0.90
    POSITIVE LOGITS
     American
    4.18
     Americans
    4.08
     America
    4.06
     USA
    3.97
    American
    3.94
    美国
    3.88
     US
    3.83
    美國
    3.81
     США
    3.77
    America
    3.77
    Activations Density 3.152%

    No Known Activations