© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5991
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connecting phrases after punctuation

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

    connecting or contrasting ideas

    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
    的話
    0.83
    的话
    0.77
    ،
    0.75
    의
    0.69
    的
    0.66
    ة
    0.62
     ،
    0.61
    の
    0.61
    的朋友
    0.61
    ፣
    0.61
    POSITIVE LOGITS
    而且
    1.35
    并且
    1.32
    并在
    1.26
    从而
    1.15
    並且
    1.15
    但在
    1.13
    但
    1.13
    但是在
    1.12
    但是
    1.10
     ხოლო
    1.09
    Activations Density 0.007%

    No Known Activations