© 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. 141518
    Prev
    Next
    INDEX
    Explanations

    predictions, if, that, for

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

    negative attributes or processing limitations

    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
    เขียน
    0.46
     និង
    0.46
     ,
    0.46
    wahl
    0.46
     הם
    0.45
    กัน
    0.45
     或
    0.45
    praw
    0.45
     και
    0.44
    是
    0.44
    POSITIVE LOGITS
     spiritually
    0.51
    وتا
    0.45
     supportive
    0.43
    +.
    0.42
    떼
    0.42
     Heavenly
    0.41
     parlor
    0.41
    飲食店
    0.41
    繁忙時間服務
    0.41
    ڳ
    0.40
    Activations Density 0.001%

    No Known Activations