© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92025
    Prev
    Next
    INDEX
    Explanations

    boat and boating activities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bicy
    -1.12
    Bicycle
    -1.05
     bicycle
    -1.05
     cyclist
    -0.98
     Bicycle
    -0.92
     volar
    -0.91
    bicycle
    -0.90
     miners
    -0.90
     cyclists
    -0.88
    Cycling
    -0.88
    POSITIVE LOGITS
     boat
    2.38
     boats
    1.99
    boat
    1.88
    boats
    1.62
     Boat
    1.62
    Boat
    1.61
     boating
    1.57
     hull
    1.48
     marine
    1.37
    船
    1.34
    Activations Density 0.064%

    No Known Activations