© 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. 103201
    Prev
    Next
    INDEX
    Explanations

    myopia and short-sightedness

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

    This neuron activates for content related to myopia (nearsightedness) and short-sightedness, both in literal medical contexts and metaphorical uses related to limited perspective.

    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
    IntOverflow
    -0.73
    catus
    -0.73
    勲
    -0.69
     Khalifa
    -0.68
    isak
    -0.68
    不被
    -0.68
     uneasiness
    -0.68
     magasins
    -0.68
     جدی
    -0.68
     المحت
    -0.67
    POSITIVE LOGITS
    sighted
    2.55
     short
    2.38
    short
    2.08
     My
    2.02
    My
    1.96
    my
    1.93
     sighted
    1.90
    短
    1.87
     my
    1.87
     mio
    1.81
    Activations Density 0.042%

    No Known Activations