© 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. 10507
    Prev
    Next
    INDEX
    Explanations

    saving and running code

    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
     dritte
    0.83
    isdigit
    0.80
     seconda
    0.79
     zweite
    0.77
    ayama
    0.74
    #######
    0.73
     weitere
    0.72
    Favorites
    0.72
     Big
    0.71
    PM
    0.71
    POSITIVE LOGITS
    選項
    1.07
     добы
    0.98
    昌
    0.93
    මණ
    0.91
    льта
    0.89
    选项
    0.89
    forcements
    0.89
    謹
    0.89
    istration
    0.88
     হৃ
    0.88
    Activations Density 0.125%

    No Known Activations