© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8387
    Prev
    Next
    INDEX
    Explanations

    global development and aid

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

    NGOs, poverty, and aid in Africa

    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
    大佬
    0.47
    🤪
    0.47
     Interstate
    0.46
     якобы
    0.45
     Famous
    0.44
    errated
    0.43
     Teut
    0.43
    weird
    0.42
    ♯
    0.42
     weird
    0.42
    POSITIVE LOGITS
     villagers
    1.27
     Malawi
    1.24
     Ugandan
    1.20
     Tanzania
    1.14
    村民
    1.14
     NGO
    1.13
     Uganda
    1.11
     Rwandan
    1.11
     USAID
    1.09
     Burkina
    1.08
    Activations Density 0.206%

    No Known Activations