© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 9467
    Prev
    Next
    INDEX
    Explanations

    EU regulations

    np_max-act-logits · gemini-2.5-flash-lite

    EU Brexit

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     Sir
    0.52
    Sir
    0.51
     Disclosure
    0.51
     Victims
    0.51
     Pont
    0.50
     vulnerable
    0.49
     setTitle
    0.49
    Փ
    0.48
     Rehabilitation
    0.48
     Vulner
    0.48
    POSITIVE LOGITS
     Brexit
    1.85
    Brexit
    1.81
     EU
    1.61
    EU
    1.51
    欧盟
    1.36
     bre
    1.34
     BRE
    1.25
     eu
    1.17
     Bre
    1.15
    BRE
    1.12
    Activations Density 0.082%

    No Known Activations