© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10120
    Prev
    Next
    INDEX
    Explanations

    การทำ

    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_22_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
    之外
    1.04
    大
    1.01
    估计
    0.94
    前
    0.93
    《
    0.91
    大了
    0.89
    和
    0.88
    头
    0.88
    大的
    0.87
    史上
    0.86
    POSITIVE LOGITS
     يكون
    1.18
     bermain
    1.18
     dibutuhkan
    1.11
     menampilkan
    1.11
     تغير
    1.11
    يكون
    1.09
     ين
    1.09
     church
    1.08
     சில
    1.07
     tund
    1.07
    Activations Density 0.001%

    No Known Activations