© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63206
    Prev
    Next
    INDEX
    Explanations

    makeup artist, designer, products

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

    The neuron fires strongly on occurrences of the term “make up” (in any form, including “makeup,” “make-up,” and brand names like “MAKE UP FOR EVER”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     carb
    -0.81
    á
    -0.78
    Curve
    -0.76
     Paste
    -0.75
    bla
    -0.74
    ¬
    -0.73
    喀
    -0.73
     Curve
    -0.73
     Pil
    -0.72
    ooo
    -0.72
    POSITIVE LOGITS
    💄
    1.33
     remover
    1.21
     artist
    1.15
     artists
    1.03
     ARTIST
    0.94
    removing
    0.88
    ǭ
    0.88
     connexe
    0.85
    落とし
    0.85
    brushes
    0.85
    Activations Density 0.010%

    No Known Activations