© 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. 59887
    Prev
    Next
    INDEX
    Explanations

    C# usings

    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
     canvas
    -0.95
     Fortnite
    -0.93
     Brexit
    -0.86
     TMPro
    -0.85
     wetland
    -0.85
     $"{
    -0.83
    istemas
    -0.80
    ($"
    -0.79
    https
    -0.79
     اله
    -0.79
    POSITIVE LOGITS
    collider
    0.94
    rigid
    0.92
    🤎
    0.88
     fundas
    0.85
    /__
    0.77
     xrange
    0.76
    gui
    0.76
     Kinect
    0.74
     للد
    0.74
     Guillermo
    0.74
    Activations Density 0.018%

    No Known Activations