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. 8227
    Prev
    Next
    INDEX
    Explanations

    European Union proceedings

    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
    
    -0.87
     flexibles
    -0.78
     أيضًا
    -0.78
     stycznia
    -0.77
    avice
    -0.75
    howto
    -0.74
    УДК
    -0.74
     residente
    -0.73
     stretchy
    -0.73
     suun
    -0.72
    POSITIVE LOGITS
     Annex
    1.12
    adone
    1.07
     divergent
    1.02
    (')
    1.01
    Annex
    1.00
     recital
    0.98
    OJ
    0.96
     tormented
    0.92
     descubrimiento
    0.88
     EU
    0.87
    Activations Density 0.014%

    No Known Activations