© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59508
    Prev
    Next
    INDEX
    Explanations

    apparel and yarn

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

    The neuron specifically detects references to apparel and other clothing or textile items.

    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
     сможет
    -3.06
    ☫
    -2.86
     видит
    -2.63
    หรือ
    -2.47
     controla
    -2.45
     transporta
    -2.38
    艄
    -2.34
    埽
    -2.33
    ⸫
    -2.27
    槼
    -2.25
    POSITIVE LOGITS
    e
    3.61
    h
    2.95
    .
    2.55
    [
    2.48
     Other
    2.48
     Suitable
    2.47
    ↵
    2.47
    真的
    2.45
    The
    2.38
    ࿚
    2.38
    Activations Density 0.010%

    No Known Activations