© 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. 13-GEMMASCOPE-2-RES-65K
    7. 442
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "" when executed directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     然而
    1.49
     而且
    1.47
     令
    1.45
     reinvigor
    1.41
     哦
    1.40
     promulg
    1.39
     任
    1.38
     monumental
    1.37
     repre
    1.36
     franch
    1.35
    POSITIVE LOGITS
    _
    1.42
    it
    1.23
    View
    1.21
    вЂ
    1.18
    view
    1.17
    ผ
    1.14
    Last
    1.11
    alex
    1.11
    izare
    1.11
    Graph
    1.10
    Activations Density 0.410%

    No Known Activations