© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17114
    Prev
    Next
    INDEX
    Explanations

    button type

    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
     perchè
    0.63
     alot
    0.56
     বেশী
    0.51
    出来る
    0.51
     কোন
    0.50
    ﮧ
    0.50
     dibawah
    0.48
     skall
    0.48
     পরিমান
    0.47
     সম্পূর্ন
    0.47
    POSITIVE LOGITS
     به‌عنوان
    0.51
    ↵
    0.46
     그다음에
    0.44
     policym
    0.42
     Afterward
    0.41
     policymakers
    0.39
     Nonprofit
    0.39
    ન્ટ
    0.38
     به‌
    0.38
    さまざまな
    0.37
    Activations Density 0.028%

    No Known Activations