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. 8446
    Prev
    Next
    INDEX
    Explanations

    currency, discounts, and numbers

    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
     flavor
    -0.98
     flavorful
    -0.89
     specializing
    -0.87
    ardized
    -0.87
     flavored
    -0.87
     Flavor
    -0.86
     colorful
    -0.82
     uchun
    -0.81
    urized
    -0.81
     behavior
    -0.81
    POSITIVE LOGITS
     £
    1.55
     reductions
    1.25
    Reduced
    1.15
     (£
    1.14
     réduire
    1.13
    -£
    1.11
    £
    1.10
     Argos
    1.05
    Tes
    1.04
    reduced
    1.01
    Activations Density 0.034%

    No Known Activations