© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15285
    Prev
    Next
    INDEX
    Explanations

    death and dying

    np_acts-logits-general · gemini-2.5-flash-lite

    death, kill, or dying

    np_acts-logits-general · gemini-2.5-flash-lite

    death

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENGTH
    0.62
    ୍ର
    0.62
    opération
    0.61
    ס
    0.59
    etat
    0.59
    TRR
    0.58
     adı
    0.57
    ಕ್ಷ
    0.57
    unfortunately
    0.57
    abbam
    0.57
    POSITIVE LOGITS
    死的
    0.80
     muerte
    0.78
     Dead
    0.76
     death
    0.75
    死
    0.74
     Death
    0.73
     chết
    0.64
     dead
    0.64
     or
    0.63
     DEATH
    0.61
    Activations Density 0.253%

    No Known Activations