© 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-262K
    7. 27275
    Prev
    Next
    INDEX
    Explanations

    European Union membership and closer ties

    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_262k_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
    鲳
    0.40
    蜡
    0.39
     savanna
    0.37
    గ్
    0.37
     petróleo
    0.37
    还原
    0.37
     subtlety
    0.36
    娥
    0.36
     glycer
    0.35
     chines
    0.35
    POSITIVE LOGITS
     EU
    0.61
    欧盟
    0.57
     Vilnius
    0.50
     Bosnia
    0.49
     यूरोपीय
    0.49
     Europese
    0.49
    EU
    0.49
     الأوروب
    0.49
    European
    0.48
    Membership
    0.47
    Activations Density 0.019%

    No Known Activations