© 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. 19328
    Prev
    Next
    INDEX
    Explanations

    thermoelectric energy conversion

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

    The neuron responds to occurrences of the substring “electric,” as in “thermoelectric” or “electric.”

    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
    呖
    -1.95
     using
    -1.63
     åren
    -1.56
    瑧
    -1.51
    芣
    -1.48
     of
    -1.46
     annuel
    -1.44
    焢
    -1.41
    Putting
    -1.40
    Время
    -1.39
    POSITIVE LOGITS
     to
    2.30
    盉
    1.85
     küçük
    1.69
            
    1.68
     if
    1.63
     Anſ
    1.63
    ໊
    1.62
                     
    1.61
    下さ
    1.61
                          
    1.59
    Activations Density 0.024%

    No Known Activations