© 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. 6960
    Prev
    Next
    INDEX
    Explanations

    names followed by roman numerals

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

    Roman numerals II and III

    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
    
    0.51
    的两
    0.47
    
    0.47
    ماس
    0.43
     दरवा
    0.41
     ($(
    0.40
     جوجل
    0.39
    两年
    0.38
    兩個
    0.38
    ളു
    0.38
    POSITIVE LOGITS
     III
    3.64
    III
    3.47
     II
    3.30
     VII
    3.19
     VIII
    3.03
     IV
    2.98
    II
    2.97
    VII
    2.89
    VIII
    2.75
    Ⅲ
    2.64
    Activations Density 0.122%

    No Known Activations