© 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. 597
    Prev
    Next
    INDEX
    Explanations

    summarization pipeline creation

    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_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
    dengan
    2.39
    pictured
    2.29
    dalam
    2.26
    അ
    2.22
    Namun
    2.19
    tidak
    2.19
    вЂ
    2.19
    mostly
    2.18
    untuk
    2.14
    lihat
    2.14
    POSITIVE LOGITS
     啊
    2.59
     也
    2.55
     哦
    2.50
     跟
    2.50
     把
    2.43
     初始化
    2.42
     可以
    2.40
     將
    2.36
    2.35
     调用
    2.33
    Activations Density 0.710%

    No Known Activations