© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52991
    Prev
    Next
    INDEX
    Explanations

    Khmer, Cambodia, Phnom Penh, Angkor

    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/layer_31_width_65k_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
     cuenta
    0.51
    潍
    0.50
     организа
    0.46
     організа
    0.46
    urrence
    0.46
    㕣
    0.46
     Muir
    0.45
     контра
    0.45
     répartition
    0.45
     Chile
    0.43
    POSITIVE LOGITS
     Khmer
    1.34
     Cambodian
    1.27
     Cambodia
    1.23
     Angkor
    1.18
     Phnom
    1.15
    柬
    0.92
     Mekong
    0.83
    Myanmar
    0.73
     Thai
    0.70
    Thai
    0.69
    Activations Density 0.015%

    No Known Activations