© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73059
    Prev
    Next
    INDEX
    Explanations

    sanitary, SATA, copic

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

    The neuron detects words related to sanitation or sterility (e.g., “sanitary,” “sanitization,” “sanitariums”).

    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
     ซึ่ง
    -2.88
    痦
    -2.72
     funcionam
    -2.69
     Which
    -2.67
     และ
    -2.66
    ajout
    -2.58
    
    -2.58
    鲠
    -2.56
     praktische
    -2.53
     Kategor
    -2.50
    POSITIVE LOGITS
    ↵↵
    3.27
    ),
    2.95
    ]
    2.78
    %
    2.59
    e
    2.38
    A
    2.38
    {\
    2.34
     []
    2.33
    -”
    2.30
    昙
    2.30
    Activations Density 0.001%

    No Known Activations