© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25614
    Prev
    Next
    INDEX
    Explanations

    cataracts and eye conditions

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

    This neuron identifies terms related to eye anatomy and eye conditions, particularly focusing on cataracts and ocular structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on specialized ophthalmology terminology, especially words referring to eye anatomy and diseases (e.g., cataracts, intraocular, cornea, retina).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    
    -0.79
     customerId
    -0.78
    vidence
    -0.78
    burgo
    -0.77
     eſ
    -0.77
    croft
    -0.75
    nne
    -0.75
    spine
    -0.75
    ervi
    -0.74
     Purdue
    -0.73
    POSITIVE LOGITS
     cornea
    1.41
     lens
    1.18
     corneal
    0.98
     cor
    0.90
     clou
    0.90
    film
    0.83
    cor
    0.83
    transparent
    0.80
     catar
    0.80
    lens
    0.80
    Activations Density 0.117%

    No Known Activations