© 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. 17-GEMMASCOPE-2-RES-16K
    7. 463
    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
    ჲ
    2.37
    ﾇ
    2.20
     პ
    2.08
     ბ
    2.06
    <unused240>
    1.98
     使い
    1.95
    <unused537>
    1.93
     おい
    1.93
    <unused218>
    1.92
     また
    1.88
    POSITIVE LOGITS
     các
    3.75
     những
    3.30
     không
    3.06
     nhiều
    3.05
     chỉ
    3.00
     thông
    3.00
     kết
    2.97
     đồng
    2.96
     sản
    2.95
     cùng
    2.91
    Activations Density 0.224%

    No Known Activations