© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    capitalized named entities—especially formal titles, institutions, places, brands, and titles of works.

    oai_token-act-pair · gpt-5Triggered by @smilgaveronika
    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
    ceau
    1.00
    <unused639>
    0.93
    撐
    0.93
    ませんので
    0.91
     갖고
    0.90
    <unused199>
    0.88
     "&#
    0.87
    ++',
    0.86
    /';
    0.86
    urator
    0.85
    POSITIVE LOGITS
     yaitu
    1.48
     bernama
    1.36
     Joe
    1.32
     olan
    1.28
     John
    1.26
     Joseph
    1.24
     iaitu
    1.23
     Kevin
    1.23
     yakni
    1.22
     José
    1.20
    Activations Density 0.801%

    No Known Activations