© 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. 48989
    Prev
    Next
    INDEX
    Explanations

    underworld and 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
     Solitude
    -0.77
    我们将
    -0.77
     Jansen
    -0.77
     Skyscanner
    -0.74
    トラック
    -0.74
    шко
    -0.73
     verifies
    -0.71
    기에
    -0.69
    bisoft
    -0.69
    hộp
    -0.69
    POSITIVE LOGITS
     underworld
    2.03
     Hades
    1.62
     Underworld
    1.53
    Hades
    1.39
    冥
    1.32
     Death
    1.29
     underground
    1.20
     death
    1.19
    death
    1.10
    Death
    1.02
    Activations Density 0.007%

    No Known Activations