© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    OECD countries, children born

    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
    煙
    1.41
    時短
    1.31
     окончания
    1.30
     ende
    1.27
     ابراہیم
    1.21
    риди
    1.21
     крайней
    1.21
     прой
    1.20
     تنس
    1.20
    enden
    1.19
    POSITIVE LOGITS
     চোখ
    1.58
     scholarship
    1.56
    algebras
    1.51
    硕
    1.50
    _|
    1.50
     oeuvre
    1.49
    osch
    1.49
     Scholarship
    1.47
     Bruder
    1.45
    fels
    1.43
    Activations Density 0.000%

    No Known Activations