© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69501
    Prev
    Next
    INDEX
    Explanations

    English, American, and related nationalities

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

    Western countries and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Malay
    0.36
    गाव
    0.36
     चाइ
    0.36
     chines
    0.35
     امی
    0.35
    蟬
    0.35
    ᓪ
    0.34
    ري
    0.34
    upi
    0.33
     chinese
    0.33
    POSITIVE LOGITS
     English
    0.66
    English
    0.62
     America
    0.61
     англий
    0.61
     American
    0.57
     آمریک
    0.56
    美国的
    0.55
     Englishmen
    0.55
     England
    0.54
     британ
    0.54
    Activations Density 0.730%

    No Known Activations