© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7857
    Prev
    Next
    INDEX
    Explanations

    verbs in -ing form

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

    The neuron strongly activates on words ending in “-ing” (i.e. gerunds/present-participle verbs).

    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
     in
    -2.53
     by
    -2.27
     it
    -2.11
     not
    -1.80
     does
    -1.73
     has
    -1.71
     can
    -1.70
     still
    -1.70
     as
    -1.67
     other
    -1.66
    POSITIVE LOGITS
     honn
    1.59
    牙齿
    1.59
     principalement
    1.58
    (“
    1.55
    衚
    1.38
     milliers
    1.38
    苙
    1.38
    橚
    1.34
     Badan
    1.33
     colis
    1.32
    Activations Density 0.087%

    No Known Activations