© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15926
    Prev
    Next
    INDEX
    Explanations

    writing and processing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     канторы
    0.38
     опубли
    0.38
     запол
    0.38
     дори
    0.37
     اخ
    0.37
    ><?
    0.37
    ிருஷ்
    0.36
     поддержи
    0.36
    を発
    0.36
     বংশ
    0.35
    POSITIVE LOGITS
    了
    0.73
    一下
    0.64
    的是
    0.63
    了一下
    0.63
    了一
    0.63
    自己的
    0.62
    到
    0.62
    其
    0.60
    了很多
    0.57
    到的
    0.54
    Activations Density 0.014%

    No Known Activations