© 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. 69416
    Prev
    Next
    INDEX
    Explanations

    beginning an action

    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
    鼷
    -1.40
    (‘
    -1.38
     guantes
    -1.35
    
    -1.34
     合集
    -1.34
     vœux
    -1.32
    
    -1.32
    ungkapkan
    -1.30
     aprobó
    -1.30
    谖
    -1.29
    POSITIVE LOGITS
     will
    1.69
     he
    1.62
     to
    1.58
     of
    1.57
     ${
    1.41
    énu
    1.41
    /*
    1.40
    0
    1.33
     *
    1.27
    s
    1.24
    Activations Density 0.022%

    No Known Activations