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. 7995
    Prev
    Next
    INDEX
    Explanations

    adjective followed by to or and

    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
     posibilidades
    -1.15
     llegamos
    -0.98
     cualidades
    -0.98
     maravill
    -0.97
     aesthetically
    -0.95
     bardzo
    -0.95
     unangemess
    -0.94
     distintas
    -0.94
     merkwür
    -0.93
     Seorang
    -0.93
    POSITIVE LOGITS
     than
    1.62
     to
    1.54
     enough
    1.48
     and
    1.19
     ones
    1.17
    ness
    1.16
    ly
    1.16
     as
    1.13
     for
    1.13
     ENOUGH
    1.08
    Activations Density 0.123%

    No Known Activations