© 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. 7122
    Prev
    Next
    INDEX
    Explanations

    washing and rinsing

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

    The neuron detects references to cleaning or removal procedures such as washing, rinsing, or flushing.

    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
    </h4>
    -1.56
     africains
    -1.36
     similarities
    -1.25
    {
    -1.24
    </h2>
    -1.24
     vollständige
    -1.23
     kirj
    -1.23
    </h3>
    -1.22
     they
    -1.20
     Dijo
    -1.19
    POSITIVE LOGITS
     asust
    1.34
     pensées
    1.31
    renched
    1.28
     stroll
    1.27
    ционер
    1.27
    етра
    1.27
    ଃ
    1.27
     harán
    1.26
    鲼
    1.25
    styleUrls
    1.24
    Activations Density 0.058%

    No Known Activations