© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3593
    Prev
    Next
    INDEX
    Explanations

    toilet paper, bowls, and habits

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

    The neuron fires on mentions of “toilet” and closely related toilet-themed terms (e.g. toilet paper, toilet training, cleaning toilets, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     interpreter
    -0.95
     JVM
    -0.85
    Фо
    -0.82
     nonce
    -0.80
    慑
    -0.79
    Wel
    -0.79
     explications
    -0.79
     Staf
    -0.78
     interpreters
    -0.78
     notary
    -0.77
    POSITIVE LOGITS
     paper
    1.45
     seat
    1.14
    paper
    1.12
     bowl
    1.09
     facilities
    0.96
     Paper
    0.95
     seats
    0.93
    Paper
    0.89
    本文
    0.86
    ries
    0.85
    Activations Density 0.022%

    No Known Activations