© 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. 34-GEMMASCOPE-RES-131K
    7. 58083
    Prev
    Next
    INDEX
    Explanations

    paper and tissues

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

    The neuron fires on mentions of paper‐based products and their dispensing hardware (e.g. paper towels, toilet-paper, napkins/tissues and dispensers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Luggage
    -0.83
    clav
    -0.80
    mixed
    -0.80
     luggage
    -0.77
    mathit
    -0.76
     cooling
    -0.76
    addMouseListener
    -0.74
    Broken
    -0.73
    paint
    -0.73
     Cliquez
    -0.72
    POSITIVE LOGITS
     tissue
    2.14
     tissues
    2.00
     toilet
    1.77
     Tissue
    1.77
     Tissues
    1.70
    Tissue
    1.66
    tissue
    1.59
     paper
    1.46
    🧻
    1.40
     rolls
    1.23
    Activations Density 0.021%

    No Known Activations