© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2470
    Prev
    Next
    INDEX
    Explanations

    after periods or tasks

    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
     by
    1.09
     or
    1.04
    sky
    1.01
     =
    0.96
     :
    0.95
    typen
    0.93
     или
    0.90
    animal
    0.88
    とは
    0.87
     /
    0.86
    POSITIVE LOGITS
     logró
    1.59
     ardından
    1.54
     trató
    1.52
     aldığı
    1.52
     decidió
    1.50
     consiguió
    1.48
     desarrolló
    1.48
     outfitted
    1.45
    该公司
    1.43
     તેમની
    1.42
    Activations Density 0.162%

    No Known Activations