© 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-16K
    7. 3448
    Prev
    Next
    INDEX
    Explanations

    Gemini and Oppenheimer names

    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_16k_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
     Fourier
    0.33
     schizophren
    0.32
     Word
    0.31
     badań
    0.30
     agglut
    0.30
    ↵
    0.29
     tranquill
    0.29
     Sche
    0.29
     MIUI
    0.29
     tête
    0.28
    POSITIVE LOGITS
     नही
    0.40
     ايضا
    0.40
     입니다
    0.40
    枼
    0.38
     পুর্ব
    0.38
    ！！！
    0.38
    aime
    0.37
    也
    0.37
    мы
    0.37
    的的
    0.37
    Activations Density 1.711%

    No Known Activations