© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2201
    Prev
    Next
    INDEX
    Explanations

    language model understanding

    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
    licka
    1.11
    ilo
    1.04
     uniformed
    1.00
    ila
    0.98
     fisik
    0.95
    Ý
    0.95
     Desen
    0.95
     planetary
    0.93
     yeast
    0.93
    രാഷ്ട്ര
    0.93
    POSITIVE LOGITS
    彙
    1.26
    spoken
    1.06
     uttered
    1.05
    mith
    1.05
    씀
    1.03
     spoken
    1.03
    嫣
    0.99
    痨
    0.96
    감이
    0.94
    뱉
    0.94
    Activations Density 0.403%

    No Known Activations