© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210201
    Prev
    Next
    INDEX
    Explanations

    mobile websites and featured lists

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

    explaining concepts using context

    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_31_width_262k_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
    錒
    0.56
    什麼
    0.55
    什么时候
    0.54
    而言
    0.52
    阿
    0.52
    其实
    0.50
    糍
    0.50
    什么
    0.49
    妙
    0.49
    玑
    0.48
    POSITIVE LOGITS
     ,
    0.50
     proprietary
    0.49
     newly
    0.47
     foule
    0.47
     jude
    0.46
     shar
    0.45
    ts
    0.45
     conforman
    0.45
     tach
    0.44
     subcl
    0.44
    Activations Density 0.000%

    No Known Activations