© 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. 59749
    Prev
    Next
    INDEX
    Explanations

    optic nerve and related conditions

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

    The neuron detects mentions of "optic" in medical or scientific contexts, particularly related to optic nerves, optic tracts, and optic neuropathies.

    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
    决
    -0.75
    requestData
    -0.72
    poison
    -0.71
    ਾਈ
    -0.69
    Poison
    -0.69
    niak
    -0.69
    hướng
    -0.68
     instructed
    -0.68
     زیست
    -0.67
    icor
    -0.67
    POSITIVE LOGITS
    vix
    0.69
    licated
    0.69
    '}';
    0.68
     વા
    0.67
     cartera
    0.65
    厨
    0.64
     speak
    0.64
     Always
    0.63
    chier
    0.63
    parquet
    0.63
    Activations Density 0.054%

    No Known Activations