© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical and regulatory compliance

    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
    伥
    0.68
    routingHeader
    0.58
    ามารถ
    0.56
    ปลี่ยน
    0.54
    喱
    0.54
    ফটেন্যান্ট
    0.53
    ्रम
    0.52
     ঘূর্ণ
    0.52
     electricians
    0.52
    堣
    0.52
    POSITIVE LOGITS
     pharmaceutical
    1.66
     drug
    1.61
     Pharmaceutical
    1.61
     pharma
    1.57
     pharmaceut
    1.52
     Pharmac
    1.51
     pharmac
    1.48
     Pharma
    1.48
    Pharmac
    1.45
    Drug
    1.41
    Activations Density 0.033%

    No Known Activations