© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5400
    Prev
    Next
    INDEX
    Explanations

    news and updates

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

    latest news and information

    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
    boBox
    0.41
     दृढ़
    0.37
    workbook
    0.37
     ಇದಕ್ಕೆ
    0.36
    ⇑
    0.36
     오랜
    0.36
    hanahu
    0.35
    兩種
    0.35
     structurally
    0.35
    셩
    0.35
    POSITIVE LOGITS
     news
    2.11
     happenings
    2.06
     noticias
    1.86
     notícias
    1.81
     новости
    1.80
    news
    1.79
     developments
    1.79
     updates
    1.74
     nieuws
    1.69
    ニュース
    1.67
    Activations Density 0.486%

    No Known Activations