© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106216
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing' or 'izing'

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

    The neuron activates on the initial subword pieces that begin longer, multi‐part words (i.e. the BPE prefixes at the start of polysyllabic words).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    verbs in their -ing (gerund/participle) form, especially activating on the stem just before the -ing suffix.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408

    word fragments ending in common suffixes or letter combinations like "-ying", "-cing", "-ting", "-ning", and "-ing" variations.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered 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
    Negative Logits
     need
    -1.67
     use
    -1.38
     struggle
    -1.30
     continued
    -1.28
     decrease
    -1.27
     more
    -1.26
     lack
    -1.23
    上がった
    -1.23
    álise
    -1.22
    ufes
    -1.21
    POSITIVE LOGITS
    ing
    2.06
    ifying
    1.84
    izing
    1.84
    jąc
    1.66
    ING
    1.59
    fying
    1.59
    οντας
    1.55
     orchestr
    1.55
    getting
    1.52
    ulating
    1.51
    Activations Density 0.098%

    No Known Activations