© 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. 83936
    Prev
    Next
    INDEX
    Explanations

    void and emptiness

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

    The main thing this neuron does is detect mentions of someone’s passing or expressions of tragic loss (e.g. “passing,” “tragic loss,” “left us,” “mourned”).

    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
    擱
    -0.78
    と呼ばれる
    -0.78
    chita
    -0.77
    niña
    -0.76
     trabalha
    -0.76
    ◅
    -0.76
    怖い
    -0.75
    ществует
    -0.75
     Fritz
    -0.75
     ferrocarril
    -0.75
    POSITIVE LOGITS
     void
    2.69
     loss
    2.39
     hole
    2.16
     vacuum
    2.02
     voids
    1.99
     emptiness
    1.98
    loss
    1.95
     vacancy
    1.80
    void
    1.78
     absence
    1.77
    Activations Density 0.025%

    No Known Activations