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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33666
    Prev
    Next
    INDEX
    Explanations

    macular degeneration AMD

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

    terms related to eye diseases and conditions, particularly macular degeneration and retinal disorders.

    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
     lens
    -1.02
     Lens
    -0.96
     lenses
    -0.85
    lens
    -0.84
     cornea
    -0.78
    Lens
    -0.78
     discounted
    -0.75
     sleep
    -0.75
     Dated
    -0.72
     eyelids
    -0.70
    POSITIVE LOGITS
    AMD
    1.34
     AMD
    1.26
     macular
    0.84
    wet
    0.82
     degeneration
    0.81
     wet
    0.78
     vitre
    0.78
    rude
    0.76
    Kuro
    0.76
     WET
    0.76
    Activations Density 0.173%

    No Known Activations