© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3472
    Prev
    Next
    INDEX
    Explanations

    Cambodia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    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
     ہوا
    0.60
    ្សែ
    0.58
     উর্দু
    0.55
    🏴
    0.55
     Lombard
    0.54
     loop
    0.54
     Gl
    0.53
    ுகள்
    0.53
     Loop
    0.52
     നിയ
    0.52
    POSITIVE LOGITS
     Cambodian
    2.22
     Khmer
    2.19
     Cambodia
    2.16
     Phnom
    2.05
     Angkor
    1.70
    柬
    1.59
    Camb
    1.30
     Mekong
    1.21
     camb
    1.20
     Siem
    1.16
    Activations Density 0.053%

    No Known Activations