© 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. 10-GEMMASCOPE-RES-131K
    7. 12643
    Prev
    Next
    INDEX
    Explanations

    words starting with Mu

    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
    
    -2.78
    ↵↵
    -2.59
    좇
    -2.58
    béco
    -2.58
    慙
    -2.50
    ⁛
    -2.47
    焌
    -2.47
     лучший
    -2.41
    
    -2.41
    らせる
    -2.39
    POSITIVE LOGITS
    1
    3.11
     It
    2.94
    {
    2.89
    >
    2.59
     Because
    2.55
    <
    2.53
    *
    2.52
     Its
    2.52
    _
    2.52
    0
    2.41
    Activations Density 0.002%

    No Known Activations