© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71241
    Prev
    Next
    INDEX
    Explanations

    being and other -ing verbs

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

    The neuron fires on verb “-ing” forms (gerunds/present participles) indicating ongoing actions or states.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     frequentemente
    -1.43
     giu
    -1.35
     staffel
    -1.31
     sanitario
    -1.30
     nomine
    -1.29
     weihnachts
    -1.29
     decorativo
    -1.28
     brasileira
    -1.26
     hintergrund
    -1.26
     why
    -1.26
    POSITIVE LOGITS
    </i>
    1.51
     an
    1.47
     as
    1.35
    इटम
    1.27
     having
    1.26
     vielleicht
    1.25
     being
    1.24
     or
    1.23
     Perhaps
    1.23
    وین
    1.23
    Activations Density 0.050%

    No Known Activations