© 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. 79337
    Prev
    Next
    INDEX
    Explanations

    Jacuzzi and bath tubs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Quran
    -0.85
     çap
    -0.79
    Ve
    -0.76
    ศ
    -0.75
    ABC
    -0.73
    ্
    -0.73
    IC
    -0.73
    フェ
    -0.71
    icum
    -0.71
    neider
    -0.70
    POSITIVE LOGITS
     tub
    2.02
     bathtub
    1.88
     Jacuzzi
    1.88
     tubs
    1.88
     jacuzzi
    1.88
     whirlpool
    1.81
     Whirlpool
    1.53
     soaking
    1.52
     Jac
    1.34
     soak
    1.29
    Activations Density 0.018%

    No Known Activations