© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93388
    Prev
    Next
    INDEX
    Explanations

    medicine and related contexts

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

    references to medicine, particularly in the context of healthcare and medical professions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    血
    -0.93
    JspWriter
    -0.93
     delights
    -0.87
    encji
    -0.83
    される
    -0.82
    美好
    -0.81
    ască
    -0.79
    Crunch
    -0.79
     Corrosion
    -0.79
     caress
    -0.79
    POSITIVE LOGITS
     cabinet
    1.35
     cabinets
    1.22
    cabinet
    1.16
    Cabinet
    1.02
     Cabinet
    0.96
     ujedno
    0.92
     cabine
    0.92
     prescribed
    0.91
    Creating
    0.86
    そういえば
    0.85
    Activations Density 0.023%

    No Known Activations