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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5682
    Prev
    Next
    INDEX
    Explanations

    democracy and governance

    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
     ব্যথা
    0.59
    发射
    0.56
    探测
    0.55
     රස
    0.55
    捞
    0.55
     gyárt
    0.54
     splashed
    0.54
     puffy
    0.54
    纹
    0.53
     QuantityOnHand
    0.51
    POSITIVE LOGITS
     democracies
    1.52
     democracy
    1.48
     democratic
    1.48
     демокра
    1.48
    democracy
    1.45
     democracia
    1.34
    democratic
    1.34
     demokrat
    1.32
     Democracy
    1.29
    民主
    1.27
    Activations Density 0.275%

    No Known Activations