© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8412
    Prev
    Next
    INDEX
    Explanations

    nationalities and American

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

    American or America

    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_53_width_65k_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
    Ubuntu
    0.50
    ubuntu
    0.43
     রাজেশ
    0.43
     gtk
    0.40
     quadratic
    0.40
    gtk
    0.40
    精灵
    0.40
    昶
    0.39
     php
    0.39
     xia
    0.38
    POSITIVE LOGITS
     American
    4.34
     американ
    4.19
    American
    4.16
     Americans
    4.09
     America
    4.06
    アメリカ
    4.03
     american
    3.98
     अमेर
    3.98
     AMERICAN
    3.91
     अमेरिकी
    3.89
    Activations Density 0.475%

    No Known Activations