© 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. 58315
    Prev
    Next
    INDEX
    Explanations

    eye, corneal, ophthal

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

    vocabulary and terminology specific to ophthalmology and eye care.

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

    The neuron strongly activates on dense, domain-specific ophthalmology and retinal-disease terminology found in scientific or medical abstracts.

    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
    zweck
    -0.77
    看着他
    -0.77
     yards
    -0.76
     dAtA
    -0.75
    ⩾
    -0.74
     cherchez
    -0.73
     لباس
    -0.72
    ccia
    -0.71
    setObjectName
    -0.71
     pensar
    -0.70
    POSITIVE LOGITS
     eye
    3.16
     eyes
    2.78
     Eye
    2.75
     ophthal
    2.73
    Eye
    2.61
     Eyes
    2.55
     ocular
    2.55
     Ophthal
    2.50
    eye
    2.39
     corneal
    2.31
    Activations Density 0.651%

    No Known Activations