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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69264
    Prev
    Next
    INDEX
    Explanations

    cosmetic surgery and procedures

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

    The neuron is tuned to detect mentions of cosmetic or plastic surgery procedures and related beauty‐treatment terms.

    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
     this
    -1.47
    됩니다
    -1.23
    <h2>
    -1.13
     glared
    -1.11
    p
    -1.08
     цветов
    -1.04
     higher
    -1.03
    1
    -1.03
     {
    
    
    -1.02
     играет
    -1.02
    POSITIVE LOGITS
    TimerTask
    1.30
     acessórios
    1.25
    WHAT
    1.20
    泓
    1.19
    tió
    1.18
     okno
    1.16
     vetores
    1.16
    üchte
    1.15
     ребёнка
    1.13
     that
    1.11
    Activations Density 0.096%

    No Known Activations