© 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
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2473
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    邬
    1.09
    ⑅
    0.98
    サーチ
    0.95
     Dusty
    0.93
    笔记
    0.93
    緋
    0.92
    歙
    0.90
    岷
    0.87
     розо
    0.87
    四川
    0.87
    POSITIVE LOGITS
    PEL
    1.78
    PAL
    1.63
    kel
    1.62
    KEL
    1.61
    pel
    1.60
    jal
    1.59
     Yal
    1.59
     NEL
    1.57
    NEL
    1.55
    zal
    1.54
    Activations Density 2.473%

    No Known Activations