© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16281
    Prev
    Next
    INDEX
    Explanations

    US and American entities

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

    US international involvement and relations

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

    US/American

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     национа
    0.55
    蒴
    0.51
     nacional
    0.50
    单一
    0.49
    Conf
    0.48
     раство
    0.47
    ষণ
    0.46
    㡺
    0.46
     রাজধানী
    0.46
     λειτουργ
    0.46
    POSITIVE LOGITS
     USAID
    0.73
     US
    0.71
     amerik
    0.65
     American
    0.62
     امریکی
    0.61
     американ
    0.61
     américain
    0.60
     ameryka
    0.59
     U
    0.59
    美國
    0.59
    Activations Density 0.194%

    No Known Activations