© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 3991
    Prev
    Next
    INDEX
    Explanations

    size of datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Yous
    0.87
    setIcon
    0.85
     Bedi
    0.84
    hood
    0.82
     Kuwait
    0.81
    ilty
    0.79
    駄
    0.78
    逝
    0.78
    unité
    0.77
     Beirut
    0.76
    POSITIVE LOGITS
     mismatched
    1.47
    sites
    1.46
     نقص
    1.46
     Chast
    1.42
     بیاکت
    1.41
     اختبار
    1.40
     Paras
    1.39
    TestSource
    1.35
     Pry
    1.34
    Site
    1.34
    Activations Density 0.045%

    No Known Activations