© 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. 85239
    Prev
    Next
    INDEX
    Explanations

    ethereum and magento

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

    The neuron activates on occurrences of specific technology product or platform names (e.g. Ethereum, Magento).

    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
    9
    -4.13
    8
    -3.84
    7
    -3.66
    3
    -3.58
    2
    -3.52
    6
    -3.52
    5
    -3.48
    4
    -3.45
    y
    -3.39
    1
    -3.17
    POSITIVE LOGITS
    鲽
    3.47
    鸶
    2.98
     agence
    2.69
    鹇
    2.64
    鈊
    2.64
    嫆
    2.56
     protocolo
    2.55
    
    2.52
     帅气
    2.50
    撣
    2.48
    Activations Density 0.003%

    No Known Activations