© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21621
    Prev
    Next
    INDEX
    Explanations

    greek origins, especially medical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    मारा
    0.42
    वनि
    0.42
    इक
    0.39
     ZO
    0.38
    ﻩ
    0.37
    VENTION
    0.37
     Оно
    0.37
     सोनी
    0.36
    طن
    0.36
     Mukherjee
    0.35
    POSITIVE LOGITS
     Begin
    0.40
    ább
    0.38
    ἀ
    0.37
     Steel
    0.36
    Steel
    0.36
     chieftain
    0.35
    ['
    0.34
    říklad
    0.34
     Beginn
    0.34
     gemeinsame
    0.34
    Activations Density 0.001%

    No Known Activations