© 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. 14416
    Prev
    Next
    INDEX
    Explanations

    many scholars; rest of

    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
    ى
    1.71
     honing
    1.37
    പടി
    1.37
    ogeny
    1.30
    kan
    1.27
    ণিজ
    1.24
    ز
    1.24
    uality
    1.23
     odd
    1.23
     رب
    1.19
    POSITIVE LOGITS
     प्रधाना
    1.90
     新款
    1.83
    整治
    1.77
     đánh
    1.76
    负责人
    1.72
    班
    1.69
     Luật
    1.62
    Ẽ
    1.62
    БУ
    1.62
     Ủy
    1.61
    Activations Density 0.032%

    No Known Activations