© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81015
    Prev
    Next
    INDEX
    Explanations

    bicycle and cycling equipment

    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
     driving
    -0.89
     Driving
    -0.82
    driving
    -0.82
    QG
    -0.76
    Motorcycle
    -0.75
    Editable
    -0.74
    WW
    -0.74
     Motorcycle
    -0.73
    tagez
    -0.73
    司
    -0.71
    POSITIVE LOGITS
     bikes
    2.05
     bicycles
    1.67
     bike
    1.56
     mountain
    1.51
     Bikes
    1.38
    bikes
    1.25
     велосипе
    1.20
     bicycle
    1.19
     vélos
    1.14
    Bikes
    1.12
    Activations Density 0.023%

    No Known Activations