© 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. 8047
    Prev
    Next
    INDEX
    Explanations

    EU political countries

    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
    e
    0.43
    部
    0.42
    座位
    0.40
     belle
    0.40
    vie
    0.39
    UAE
    0.39
     Sudanese
    0.39
    គ
    0.38
    football
    0.38
    _
    0.38
    POSITIVE LOGITS
     europé
    0.53
     Demokrat
    0.50
     الأوروب
    0.50
    歐洲
    0.49
     NATO
    0.48
     Søren
    0.48
    加入
    0.48
    欧盟
    0.48
     Harald
    0.46
     Recep
    0.46
    Activations Density 0.079%

    No Known Activations