© 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. 74899
    Prev
    Next
    INDEX
    Explanations

    perfume and perfusion

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

    words related to perfumes and blood perfusion in medical contexts.

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

    This neuron activates on words beginning with the root “perf-,” such as “perfume,” “perfumed,” and “perfusion.”

    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
    ('
    -2.95
     flagrant
    -2.75
     bzw
    -2.48
    3
    -2.47
     crafty
    -2.45
    ৢ
    -2.41
    7
    -2.38
    4
    -2.34
    仅
    -2.34
     proverbial
    -2.33
    POSITIVE LOGITS
    .
    2.91
    тории
    2.70
     itſelf
    2.59
    y
    2.38
     内衣
    2.31
     墊
    2.25
    ↵
    2.25
    逦
    2.23
    <i>
    2.23
    ቷ
    2.22
    Activations Density 0.002%

    No Known Activations