© 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. 22-GEMMASCOPE-RES-131K
    7. 36109
    Prev
    Next
    INDEX
    Explanations

    people who died

    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_22/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
    уса
    -0.85
    が多い
    -0.84
    Success
    -0.84
    なら
    -0.83
    Ai
    -0.82
     produz
    -0.81
    :
    -0.80
    je
    -0.80
    देश
    -0.80
    Reset
    -0.79
    POSITIVE LOGITS
     died
    1.39
     beloved
    1.27
     death
    1.11
     deaths
    1.11
     our
    1.11
     loved
    1.08
     (†
    1.05
     muere
    1.03
     avanzada
    1.03
     valuable
    1.03
    Activations Density 0.033%

    No Known Activations