© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90279
    Prev
    Next
    INDEX
    Explanations

    conjunctions or contrast after punctuation

    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_10/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
     vogel
    -1.64
     pittores
    -1.62
     leiden
    -1.59
     latine
    -1.54
     gangen
    -1.54
     brune
    -1.52
     BIBLIOGRAPHY
    -1.51
     ciment
    -1.49
     douane
    -1.48
     forfait
    -1.47
    POSITIVE LOGITS
     but
    2.28
     or
    2.08
     for
    2.00
     because
    1.77
     on
    1.73
     after
    1.72
     most
    1.70
     blissful
    1.68
     instead
    1.55
     Almost
    1.53
    Activations Density 0.220%

    No Known Activations