© 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. 67470
    Prev
    Next
    INDEX
    Explanations

    parentheses and curly braces

    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_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
     restoran
    -1.07
     gruppe
    -1.06
     olje
    -0.98
     mavi
    -0.94
     gramos
    -0.92
     dagar
    -0.91
     verbe
    -0.89
     ferie
    -0.88
     jeudi
    -0.87
     Тран
    -0.87
    POSITIVE LOGITS
     and
    1.12
     but
    1.07
    是一位
    1.00
    人
    0.99
    做
    0.96
     واض
    0.94
     necessity
    0.92
     تحت
    0.92
    大家
    0.91
    Ɂ
    0.91
    Activations Density 0.003%

    No Known Activations