© 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. 239890
    Prev
    Next
    INDEX
    Explanations

    be or being followed by participle

    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
     bubbles
    0.57
    向け
    0.47
    듬
    0.46
    وع
    0.46
    හ
    0.46
    ተ
    0.45
    ٺ
    0.45
    یر
    0.45
     insieme
    0.43
     simplices
    0.43
    POSITIVE LOGITS
     ম্যানেজার
    0.49
    鲈
    0.47
    ছাড়া
    0.47
    脯
    0.46
     সম্ভাব্য
    0.46
     কলকাতা
    0.46
     บอก
    0.45
    indentLevel
    0.45
    köy
    0.45
    AndKeys
    0.45
    Activations Density 0.001%

    No Known Activations