© 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. 170579
    Prev
    Next
    INDEX
    Explanations

    anonymous chat

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

    minute hour cron syntax

    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
    Negative Logits
     supernat
    0.51
     جمله
    0.48
     Lark
    0.47
     منهم
    0.47
     takePhotoButton
    0.46
     عفوا
    0.45
    "-------
    0.45
     فور
    0.44
     تعلم
    0.44
     लकार
    0.44
    POSITIVE LOGITS
     borrowing
    0.51
    借
    0.50
    ends
    0.48
    ὠ
    0.48
    contacts
    0.47
    it
    0.46
    bo
    0.46
    bs
    0.45
    ct
    0.45
    il
    0.45
    Activations Density 0.001%

    No Known Activations