© 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. 116626
    Prev
    Next
    INDEX
    Explanations

    common phrases and titles

    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
     traditionally
    -1.10
     Traditionally
    -1.00
    television
    -0.94
    omsday
    -0.91
     Typically
    -0.90
     بسبب
    -0.88
     acrylic
    -0.85
    Countdown
    -0.85
     configuration
    -0.85
    heses
    -0.85
    POSITIVE LOGITS
     Xmas
    1.03
     aeroplane
    0.98
    proposition
    0.98
    -};
    0.98
     Prohibition
    0.95
     dainty
    0.91
     proposition
    0.90
    Motor
    0.89
     bungalow
    0.89
     saxophone
    0.88
    Activations Density 0.029%

    No Known Activations