© 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. 9577
    Prev
    Next
    INDEX
    Explanations

    death of parents or loved ones

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

    The neuron detects explicit mentions of someone’s death (e.g., died, death, passed away).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    !
    -1.04
     are
    -1.02
     commanded
    -0.97
    GeneratedMessage
    -0.96
    ayam
    -0.91
     if
    -0.88
     to
    -0.88
     unmodified
    -0.88
     voldoende
    -0.87
    ↵
    -0.87
    POSITIVE LOGITS
    ulieren
    1.26
     death
    1.13
     disease
    1.09
    Kamu
    1.08
     perpé
    1.07
    })}
    1.06
    fektions
    1.06
    ?></
    1.06
     whom
    1.05
     illness
    1.05
    Activations Density 0.017%

    No Known Activations