© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92276
    Prev
    Next
    INDEX
    Explanations

    Italian shoemakers marketplace trunk mats nonviolent protest

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

    latex tikz code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     JHEP
    0.50
     ਪਰ
    0.47
     நிச்சயம்
    0.45
    ச்
    0.45
     สา
    0.45
    」
    0.44
     sodass
    0.44
     ব
    0.43
     செ
    0.43
     सुनिश्चित
    0.43
    POSITIVE LOGITS
    cookieParser
    0.49
    ية
    0.46
    ემა
    0.46
     loam
    0.43
     ethylene
    0.42
    をお
    0.42
     ethic
    0.42
    MessageHandler
    0.42
    ئة
    0.40
     elems
    0.40
    Activations Density 0.000%

    No Known Activations