© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118719
    Prev
    Next
    INDEX
    Explanations

    pupil dilation or miosis

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

    terms and features related to eyes, pupils, and vision conditions.

    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
    壳
    -0.74
    kyard
    -0.73
    olla
    -0.71
     overboard
    -0.71
    Biz
    -0.70
     Pira
    -0.69
     Andi
    -0.69
    culated
    -0.69
     существует
    -0.69
     شمار
    -0.69
    POSITIVE LOGITS
     pupils
    2.72
     pupil
    2.64
    Pup
    2.14
     pup
    2.06
    pup
    2.03
    pupil
    2.03
     dilation
    1.86
     Pupils
    1.85
     dilated
    1.81
     Pupil
    1.77
    Activations Density 0.033%

    No Known Activations