© 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. 7-GEMMASCOPE-2-RES-16K
    7. 103
    Prev
    Next
    INDEX
    Explanations

    current events and progress

    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_7_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
    ؛
    1.69
     و
    1.55
    ،
    1.53
    ・・・
    1.48
     untuk
    1.48
    ۔
    1.46
    ؟
    1.45
    。...
    1.45
     för
    1.43
    :...
    1.41
    POSITIVE LOGITS
    sof
    1.60
    ClientRect
    1.52
    burned
    1.52
    ()<<
    1.50
    IPAL
    1.49
     ofthe
    1.49
    epan
    1.47
    ()<<"
    1.45
    Შ
    1.45
    bote
    1.43
    Activations Density 3.838%

    No Known Activations