© 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. 8765
    Prev
    Next
    INDEX
    Explanations

    demonstrative this/that

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

    referring to this or that

    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
     ওই
    1.07
     Этот
    1.00
     aquela
    0.98
     этой
    0.97
     该
    0.95
    Этот
    0.95
     tej
    0.93
    在该
    0.93
    該
    0.91
    ওই
    0.91
    POSITIVE LOGITS
     isso
    2.05
     cela
    1.79
     esto
    1.70
     ello
    1.70
     это
    1.66
     això
    1.56
    这一点
    1.55
     isto
    1.51
     bunu
    1.44
     eso
    1.42
    Activations Density 0.148%

    No Known Activations