© 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. 72867
    Prev
    Next
    INDEX
    Explanations

    house and subsequent terms

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

    The neuron consistently fires on occurrences of the standalone word “house.”

    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
    淠
    -2.23
     unſ
    -1.99
    鲧
    -1.87
    깬
    -1.85
    砗
    -1.84
    快要
    -1.83
    ௅
    -1.82
     frequentemente
    -1.80
    猡
    -1.77
    휀
    -1.73
    POSITIVE LOGITS
    al
    2.17
    er
    2.00
    內的
    1.98
     '-':
    1.97
    (\
    1.91
     teilweise
    1.87
    彻
    1.83
    {
    1.82
    at
    1.78
    话说
    1.76
    Activations Density 0.020%

    No Known Activations