© 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. 75100
    Prev
    Next
    INDEX
    Explanations

    mortar and brick-and-mortar locations

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

    The neuron strongly responds to words beginning with the “mort-” stem (e.g. mortar, mortars, mortuary).

    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
     большие
    -3.19
    苤
    -2.89
    艄
    -2.81
    webtoken
    -2.78
     ซึ่ง
    -2.77
    떳
    -2.73
    轳
    -2.69
    簠
    -2.67
    ཥ
    -2.67
     такие
    -2.67
    POSITIVE LOGITS
    Y
    3.13
     dictate
    2.47
     That
    2.44
    但这
    2.34
    to
    2.30
    e
    2.28
     становится
    2.22
     striving
    2.20
     Those
    2.20
    ↵
    2.20
    Activations Density 0.003%

    No Known Activations