© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8316
    Prev
    Next
    INDEX
    Explanations

    phú ông, Hoan Chau Cach, Cửu Long, pagodas, nghĩa trang

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

    thủ đô, Cao Lau, jiangshi

    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
    ছোট
    0.48
    emet
    0.48
    ਓ
    0.47
    Tipo
    0.46
     rask
    0.46
    เรีย
    0.46
    Jenis
    0.45
    𝗋
    0.45
    들어
    0.45
     প্রাথমিক
    0.44
    POSITIVE LOGITS
     lục
    0.77
     ngũ
    0.75
     thượng
    0.73
     Tử
    0.70
     cương
    0.70
     thần
    0.68
     tướng
    0.68
     đức
    0.65
     đạo
    0.65
     hậu
    0.64
    Activations Density 0.003%

    No Known Activations