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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14449
    Prev
    Next
    INDEX
    Explanations

    educational, academic, and research institutions

    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
     if
    -2.20
     up
    -1.61
     –
    -1.42
     "
    -1.41
     del
    -1.39
     most
    -1.33
     well
    -1.30
    HStack
    -1.30
     Post
    -1.27
     now
    -1.26
    POSITIVE LOGITS
     boya
    1.72
     rire
    1.59
     fuir
    1.59
     概要
    1.52
     jedynie
    1.48
     chèvre
    1.46
     सत्यापित
    1.45
     hias
    1.45
    companyId
    1.40
    諉
    1.40
    Activations Density 0.333%

    No Known Activations