© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5652
    Prev
    Next
    INDEX
    Explanations

    하셔서, 싶을, 보이곤

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

    verb stems with grammatical endings

    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
    されました
    0.58
    もあります
    0.54
    க்கள்
    0.52
    となります
    0.52
     ഉണ്ട്
    0.52
     করছে
    0.52
    があるので
    0.51
     చేశారు
    0.51
     دارد
    0.50
    の一つ
    0.50
    POSITIVE LOGITS
    도록
    0.88
    려고
    0.87
    겠다는
    0.86
    려는
    0.82
    거나
    0.79
    던
    0.76
    는데
    0.74
    었던
    0.73
    았던
    0.72
    게
    0.70
    Activations Density 0.006%

    No Known Activations