© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100734
    Prev
    Next
    INDEX
    Explanations

    cosmetics, liner, eye-pencil

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

    The neuron activates on mentions of eye‐makeup products (e.g. mascara, gel eyeliner, kajal).

    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
     But
    -3.08
    ⸫
    -2.88
    ﱠ
    -2.67
    䊐
    -2.47
     monasterio
    -2.47
    籥
    -2.42
    轳
    -2.42
    艄
    -2.41
    凊
    -2.39
    饪
    -2.38
    POSITIVE LOGITS
    e
    2.75
    '
    2.20
    这一次
    2.17
    壜
    2.17
    ↵↵
    2.09
    1
    2.03
    </h1>
    1.95
    .
    1.91
    四处
    1.90
     oll
    1.88
    Activations Density 0.001%

    No Known Activations