© 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. 84937
    Prev
    Next
    INDEX
    Explanations

    sneaker reselling and raffles

    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
     Probe
    -0.78
    祚
    -0.75
     Hum
    -0.75
     Hug
    -0.73
     Hör
    -0.72
    体に
    -0.72
    готовить
    -0.69
     hát
    -0.69
     Body
    -0.69
     Ex
    -0.69
    POSITIVE LOGITS
     sneaker
    1.41
     Sneaker
    1.16
     raffle
    1.13
     sneakers
    1.10
    sneaker
    1.08
     consignment
    1.04
    Sne
    0.96
     resell
    0.92
     Raffle
    0.90
     streetwear
    0.88
    Activations Density 0.010%

    No Known Activations