© 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. 10-GEMMASCOPE-RES-131K
    7. 102683
    Prev
    Next
    INDEX
    Explanations

    ocular anatomy and medical conditions

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

    This neuron activates for terms related to the eye and vision, including anatomical parts like "eye", "retina", "ocular", and "lens".

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

    The neuron activates on anatomical terms referring to the eye or its structures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -1.91
    </em>
    -1.91
    of
    -1.63
    [
    -1.55
    䛗
    -1.46
    際には
    -1.41
     of
    -1.40
    筱
    -1.38
     into
    -1.37
     všechny
    -1.35
    POSITIVE LOGITS
    犛
    1.50
     other
    1.49
    ܜ
    1.45
    Donativos
    1.43
    engertian
    1.40
    replyreport
    1.38
    ☆☆☆☆
    1.35
    ⽼
    1.35
     Menurut
    1.34
     compañías
    1.34
    Activations Density 0.032%

    No Known Activations