© 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. 34-GEMMASCOPE-RES-131K
    7. 59094
    Prev
    Next
    INDEX
    Explanations

    death and dying

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

    This neuron lights up on very high-frequency, common tokens—especially short function words (e.g. on, its, to, he, his) and other frequent words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Fukushima
    -0.81
    MCU
    -0.79
    cher
    -0.76
     equator
    -0.75
    缨
    -0.75
    ristol
    -0.73
    zheng
    -0.72
     Mandala
    -0.72
    Specifiche
    -0.72
    trs
    -0.71
    POSITIVE LOGITS
     dying
    3.89
    dying
    2.88
     Dying
    2.72
    Dying
    2.58
     умира
    2.13
     death
    2.05
    临
    1.84
    臨
    1.73
     last
    1.66
     morrer
    1.55
    Activations Density 0.041%

    No Known Activations