© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192175
    Prev
    Next
    INDEX
    Explanations

    bird-like blooms and Flu

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     tránh
    0.40
    kva
    0.40
    徝
    0.38
    抜
    0.38
     ջ
    0.38
    淆
    0.37
    IODevice
    0.36
     voix
    0.36
    ઐ
    0.36
     教
    0.35
    POSITIVE LOGITS
     McCullough
    0.43
     bhavati
    0.40
     menerima
    0.39
    setHorizontal
    0.39
    asmussen
    0.38
     Rasmussen
    0.37
    ipsis
    0.37
    puted
    0.37
     namely
    0.36
    tores
    0.36
    Activations Density 0.002%

    No Known Activations