© 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. 16-GEMMASCOPE-2-RES-262K
    7. 90648
    Prev
    Next
    INDEX
    Explanations

    software and system upgrades

    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/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     እና
    0.70
     إنه
    0.66
     অথবা
    0.64
    બે
    0.64
     ക
    0.64
     تحميل
    0.64
     oppure
    0.63
    ̣c
    0.62
     ktoś
    0.62
     كلمات
    0.62
    POSITIVE LOGITS
    ↵↵
    0.73
     upgrade
    0.65
    ر
    0.64
     fuss
    0.64
     upgrad
    0.62
     upgrades
    0.61
    ل
    0.59
     tariff
    0.58
     upgrading
    0.58
     Upgrade
    0.58
    Activations Density 0.004%

    No Known Activations