© 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. 112478
    Prev
    Next
    INDEX
    Explanations

    past participles after "has"

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

    This neuron detects the auxiliary verb “has,” especially when it appears in perfect‐tense constructions.

    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
    aneity
    -2.03
    wares
    -1.96
    byes
    -1.94
    onomies
    -1.88
    刧
    -1.83
     of
    -1.80
    mindedness
    -1.80
    鮡
    -1.77
    グルト
    -1.76
    melons
    -1.76
    POSITIVE LOGITS
     podríamos
    1.94
     Could
    1.89
     podría
    1.85
     naše
    1.79
     be
    1.79
     pourrait
    1.69
     könnte
    1.66
     our
    1.66
     otros
    1.64
    有沒有
    1.64
    Activations Density 0.176%

    No Known Activations