© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 53888
    Prev
    Next
    INDEX
    Explanations

    court proceedings and Louisiana judges

    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
    orea
    -0.97
     Toronto
    -0.95
     Okan
    -0.93
     zapro
    -0.91
    ijuana
    -0.90
     Ontario
    -0.87
     Vancouver
    -0.86
    Toronto
    -0.84
     Saskatoon
    -0.82
    neuron
    -0.80
    POSITIVE LOGITS
     Louisiana
    2.69
    Louisiana
    2.59
     LSU
    2.38
    LSU
    2.16
     Baton
    2.13
     Bayou
    2.05
     Shreveport
    1.85
     Cajun
    1.71
     Mardi
    1.70
     Tulane
    1.65
    Activations Density 0.234%

    No Known Activations