© 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. 14070
    Prev
    Next
    INDEX
    Explanations

    Chinese pinyin syllables

    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
    Gs
    2.28
    Ã
    2.10
    Ä
    2.07
    Ă
    2.06
    Г
    2.02
    Э
    1.99
    ukan
    1.95
    ज़
    1.91
    Å
    1.89
    ros
    1.88
    POSITIVE LOGITS
    ேட்
    2.63
    ↵↵↵↵↵
    2.26
     {//
    2.16
    ↵↵↵↵↵↵
    2.15
    e
    2.14
    vrez
    2.07
    ೋಪ
    2.06
    ோவின்
    2.02
    cated
    2.01
    고
    2.01
    Activations Density 0.092%

    No Known Activations