© 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-16K
    7. 42
    Prev
    Next
    INDEX
    Explanations

    SAP, networks, of, Die

    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_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
     สามารถ
    0.90
     ค
    0.89
     เ
    0.89
     แ
    0.88
     มี
    0.85
     ดี
    0.85
     可以
    0.85
     หมาย
    0.84
     ป
    0.84
     ส
    0.83
    POSITIVE LOGITS
     zahlreichen
    0.97
     myriad
    0.90
     jeweiligen
    0.88
     newfound
    0.83
     vergangenen
    0.83
     jeweil
    0.82
     cinquième
    0.81
     birkaç
    0.78
     successive
    0.77
     zwölf
    0.77
    Activations Density 8.792%

    No Known Activations