© 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. 34-GEMMASCOPE-RES-131K
    4. 110809
    Prev
    Next
    INDEX
    Explanations

    liquid crystal and programming includes

    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
    berton
    -0.76
    Ӱ
    -0.73
    зі
    -0.71
    parker
    -0.71
     copiar
    -0.70
     Folly
    -0.69
    Jong
    -0.69
    waniu
    -0.68
    fär
    -0.66
     photoshoot
    -0.65
    POSITIVE LOGITS
     LCD
    1.45
     Liquid
    1.45
     liquid
    1.39
    Liquid
    1.34
    LCD
    1.16
    liquid
    1.16
     lcd
    1.14
    lcd
    1.11
     LIQUID
    0.94
     Display
    0.90
    Activations Density 0.039%

    No Known Activations