© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86407
    Prev
    Next
    INDEX
    Explanations

    underwear fabrics

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

    The neuron activates on occurrences of the word “underwear.”

    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
    ’
    -3.00
    vantaged
    -2.94
    "
    -2.88
    ...
    -2.41
     \
    -2.38
    0
    -2.36
    ized
    -2.31
    “
    -2.27
     amely
    -2.27
     fueron
    -2.23
    POSITIVE LOGITS
    骉
    2.69
    嵎
    2.63
    越來
    2.48
     crescente
    2.48
    𓐍
    2.47
    quelize
    2.44
    
    2.38
     动漫
    2.36
     réfrig
    2.34
    栳
    2.34
    Activations Density 0.002%

    No Known Activations