© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12690
    Prev
    Next
    INDEX
    Explanations

    interleukin 6

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric and technical identifiers, particularly in document codes, formulas, and scientific publications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     его
    -1.09
     it
    -1.00
     każdy
    -0.93
    {}{
    -0.90
     baratos
    -0.89
    ッポン
    -0.88
     jego
    -0.87
    kými
    -0.86
     vendidos
    -0.86
     każde
    -0.85
    POSITIVE LOGITS
    了许多
    1.14
     another
    1.08
    self
    0.91
     new
    0.91
     first
    0.90
    了不少
    0.90
     simpler
    0.89
     poteva
    0.89
     sixth
    0.88
     seventh
    0.88
    Activations Density 0.000%

    No Known Activations