Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 138
    Prev
    Next
    INDEX
    Explanations

    cash register purchase transfer

    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
     shop
    -0.79
    shop
    -0.78
     lachen
    -0.75
     warehouse
    -0.72
     enumer
    -0.71
     stores
    -0.71
     retailers
    -0.71
     shopkeeper
    -0.71
    Shop
    -0.70
    Retail
    -0.70
    POSITIVE LOGITS
     member
    0.89
     holds
    0.83
    客
    0.81
     hold
    0.78
     camicia
    0.77
     split
    0.76
    ]?.
    0.76
     آموزشی
    0.75
     Holds
    0.75
    会员
    0.75
    Activations Density 0.004%

    No Known Activations