© 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. 748
    Prev
    Next
    INDEX
    Explanations

    past medical history

    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
     มัน
    0.52
     प्रसंस्करण
    0.52
    รรค
    0.52
    <unused209>
    0.52
     ถ้า
    0.52
     অ্যাপ্লিকেশন
    0.51
     normalmente
    0.51
    <unused558>
    0.50
    ឡិច
    0.50
    หมือน
    0.49
    POSITIVE LOGITS
     comorbid
    0.67
     History
    0.66
     unremarkable
    0.66
     complaints
    0.65
     EtOH
    0.65
     admitted
    0.64
     history
    0.64
     pertinent
    0.63
     Patient
    0.63
     complain
    0.62
    Activations Density 0.069%

    No Known Activations