© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108058
    Prev
    Next
    INDEX
    Explanations

    sudden death

    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
    litian
    -0.77
     Committed
    -0.76
    DECLARATION
    -0.73
    باع
    -0.71
    babwe
    -0.71
    ROME
    -0.71
     Wound
    -0.70
    bonjour
    -0.70
    icel
    -0.68
    Committed
    -0.68
    POSITIVE LOGITS
     sudden
    1.59
     Sudden
    1.26
    Sudden
    1.20
     athlete
    1.16
     athletes
    1.05
    sud
    1.03
     genetic
    1.02
     unexplained
    0.98
     suddenly
    0.97
     deaths
    0.95
    Activations Density 0.095%

    No Known Activations