© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 34778
    Prev
    Next
    INDEX
    Explanations

    Phnom Penh, Cambodia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    鳞
    0.48
    ั้น
    0.41
    ท์
    0.39
    ศาสตร์
    0.38
    িণী
    0.38
     ایران
    0.38
     महाराष्ट
    0.38
     மும்ப
    0.37
    বাচক
    0.37
     মহারা
    0.37
    POSITIVE LOGITS
     Khmer
    2.00
     Cambodian
    1.94
     Cambodia
    1.87
     Angkor
    1.76
     Phnom
    1.74
    柬
    1.55
    Camb
    1.25
     Siem
    1.20
     camb
    1.04
     Camb
    1.03
    Activations Density 0.003%

    No Known Activations