© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10177
    Prev
    Next
    INDEX
    Explanations

    in different languages

    np_acts-logits-general · gemini-2.5-flash-lite

    function words—especially auxiliaries, modals, prepositions, and interrogatives—that signal and structure user questions and informational requests.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     stets
    0.32
     Tuttavia
    0.31
    );
    0.30
     undo
    0.30
    calculated
    0.30
    ):
    0.29
     Mitarbeit
    0.28
            
    0.28
     Nacht
    0.28
     dogged
    0.28
    POSITIVE LOGITS
    для
    0.36
    ?/
    0.35
    สำหรับ
    0.34
     بۆ
    0.34
     कोलो
    0.34
     برای
    0.33
    介紹
    0.33
     examples
    0.33
    пуляр
    0.33
     для
    0.32
    Activations Density 0.513%

    No Known Activations