© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5106
    Prev
    Next
    INDEX
    Explanations

    game, phim, học bài

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

    refusal using "as such"

    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
     dependences
    0.49
     proportionality
    0.46
     грошы
    0.46
    скім
    0.46
     axonal
    0.46
    рыя
    0.46
     travailleurs
    0.46
    ჷ
    0.46
    ፉ
    0.45
    ݢ
    0.45
    POSITIVE LOGITS
     bài
    1.28
     Bài
    1.20
    Bài
    1.03
     môn
    1.00
     luyện
    0.93
     tập
    0.88
     học
    0.88
     đề
    0.87
     Giáo
    0.83
     chương
    0.80
    Activations Density 0.001%

    No Known Activations