© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10464
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    medical conditions and treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    连续
    0.36
    纲
    0.34
    比赛
    0.32
    变化
    0.32
    页面
    0.31
    Billboard
    0.31
     دنی
    0.31
    跃
    0.31
    预览
    0.31
    Geometry
    0.30
    POSITIVE LOGITS
     opioid
    0.48
     opioids
    0.47
     antimicrobial
    0.46
     antibiot
    0.45
     antifungal
    0.45
     infek
    0.45
     autoimmune
    0.44
     prostate
    0.44
     inducible
    0.44
     sepsis
    0.43
    Activations Density 0.000%

    No Known Activations