© 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. 41516
    Prev
    Next
    INDEX
    Explanations

    word stems with suffixes

    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
    姈
    -3.09
    蠵
    -2.55
    ⚋
    -2.33
     Erwart
    -2.27
     impetus
    -2.22
    ized
    -2.19
    趼
    -2.16
    迓
    -2.13
    
    -2.13
    litten
    -2.13
    POSITIVE LOGITS
    -
    2.88
     There
    2.58
    {
    2.56
    UREAU
    2.22
     wunderbar
    2.14
    with
    2.11
     I
    2.09
    ↵
    2.05
    ments
    1.95
    ússia
    1.93
    Activations Density 0.377%

    No Known Activations