© 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. 1981
    Prev
    Next
    INDEX
    Explanations

    откры кажется снима люблю

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

    small children

    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
    ၌
    0.52
    下列
    0.52
     ایالات
    0.50
     constituyen
    0.49
     proteolytic
    0.49
    তিপ
    0.48
    अधिकांश
    0.48
    頗
    0.48
     omfatt
    0.47
     گستر
    0.47
    POSITIVE LOGITS
     вот
    1.02
     тут
    1.02
     чтоб
    0.99
     малень
    0.93
     кто
    0.92
     нужно
    0.91
     хоть
    0.91
     наверное
    0.89
     просто
    0.88
     тоже
    0.88
    Activations Density 0.015%

    No Known Activations