© 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. 128714
    Prev
    Next
    INDEX
    Explanations

    related to eye medical care

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

    words related to ophthalmology, particularly terms like "ophthalmic" and other eye-related medical terminology.

    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_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
    鹇
    -2.80
    鹋
    -2.64
    ſelf
    -2.64
    鸶
    -2.61
    )
    -2.55
    aphne
    -2.45
    眼前的
    -2.39
     chuť
    -2.38
    渙
    -2.38
    quirer
    -2.34
    POSITIVE LOGITS
    “
    3.00
    2
    2.94
    E
    2.69
    I
    2.56
    ܜ
    2.53
    O
    2.50
    </i>
    2.48
    </h3>
    2.47
    <td>
    2.42
    ”:
    2.41
    Activations Density 0.005%

    No Known Activations