© 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. 84129
    Prev
    Next
    INDEX
    Explanations

    arrests and jail booking

    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
    噌
    -0.84
    Radiation
    -0.77
     eosin
    -0.76
     Cloth
    -0.76
     Dany
    -0.73
     Hoof
    -0.72
     Dues
    -0.72
     Émile
    -0.72
     dyed
    -0.71
    ulemon
    -0.71
    POSITIVE LOGITS
     booking
    3.42
     mug
    3.39
    booking
    2.86
    Booking
    2.72
     Booking
    2.69
     booked
    2.52
     Mug
    2.50
    Mug
    2.44
    mug
    2.41
     bookings
    2.33
    Activations Density 0.040%

    No Known Activations