© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4373
    Prev
    Next
    INDEX
    Explanations

    This neuron detects the word “presence,” especially in phrases like “the presence of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    tting
    0.88
     Reputation
    0.78
    лизация
    0.78
     Bản
    0.77
     Editorial
    0.75
    ometry
    0.74
    )`,
    0.74
    janje
    0.73
     Engines
    0.73
     Entertain
    0.73
    POSITIVE LOGITS
     имеется
    0.95
    اے
    0.93
     наличии
    0.91
     rashes
    0.88
    い
    0.87
     metabolites
    0.86
     ripples
    0.85
    迌
    0.85
     aanwezig
    0.84
     имеются
    0.83
    Activations Density 0.003%

    No Known Activations