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. 17
    Prev
    Next
    INDEX
    Explanations

    rarity and uncommonness

    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
     toughness
    -0.87
     tradicional
    -0.84
    getUrl
    -0.81
     majesty
    -0.75
     içinde
    -0.75
    自在
    -0.75
    glieder
    -0.75
    wisata
    -0.75
     or
    -0.75
    chaffenheit
    -0.75
    POSITIVE LOGITS
     rare
    1.32
     frequency
    1.18
     Frequency
    1.16
     rarity
    1.14
    Frequency
    1.13
     population
    1.13
     uncommon
    1.13
     rarer
    1.11
     RARE
    1.10
    requency
    1.08
    Activations Density 0.003%

    No Known Activations