© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 638
    Prev
    Next
    INDEX
    Explanations

    commas introducing examples

    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_17_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
    ,
    1.39
    ،
    1.34
    、
    1.18
    ，
    1.00
    /
    0.93
    ,/
    0.78
    、（
    0.76
    ;
    0.75
    、『
    0.73
    =
    0.73
    POSITIVE LOGITS
     valamint
    1.10
     namely
    1.02
     which
    1.01
     ktorý
    0.99
     especially
    0.99
     ktorá
    0.99
     která
    0.98
     albeit
    0.98
     respectively
    0.97
     nonché
    0.96
    Activations Density 2.468%

    No Known Activations