© 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. 113617
    Prev
    Next
    INDEX
    Explanations

    sprinkler systems, list of, Lady Gaga

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

    The neuron activates on mentions of irrigation and fire‐sprinkler systems and related components.

    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
    4
    -1.86
    ↵
    -1.85
    2
    -1.79
    {
    -1.66
    s
    -1.65
    9
    -1.64
     seiner
    -1.59
    7
    -1.56
    of
    -1.50
    -
    -1.50
    POSITIVE LOGITS
    ızlık
    1.75
     firstly
    1.72
     latar
    1.72
     nowa
    1.72
     marcadas
    1.69
     poderoso
    1.62
     decoradas
    1.61
     Сайт
    1.60
     usamos
    1.60
     facultad
    1.59
    Activations Density 0.008%

    No Known Activations