© 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. 26592
    Prev
    Next
    INDEX
    Explanations

    publish/subscribe messaging

    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
     لله
    0.42
    طاء
    0.41
    仕上げ
    0.40
    胱
    0.40
    稔
    0.40
    ಗ್ಗ
    0.39
     cramping
    0.39
    腻
    0.38
     renfer
    0.38
     cramps
    0.38
    POSITIVE LOGITS
    Publish
    1.09
     Publishers
    1.07
     Publish
    1.04
    publish
    1.03
     Subscribe
    1.02
     publisher
    1.01
    Subscribe
    1.01
    topic
    0.98
     publishers
    0.98
     Publisher
    0.98
    Activations Density 0.003%

    No Known Activations