© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75789
    Prev
    Next
    INDEX
    Explanations

    do does did

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

    The neuron strongly activates on personal group–referencing pronouns (especially “we,” “they,” and similar plural pronouns).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    なのに
    -0.89
    caba
    -0.84
     estas
    -0.82
     BONUS
    -0.81
     yanı
    -0.81
    不用
    -0.81
     ayrıca
    -0.80
     beż
    -0.79
     berperan
    -0.79
    jetty
    -0.79
    POSITIVE LOGITS
     does
    4.16
     did
    4.06
     do
    3.98
    确实
    3.09
    確實
    2.78
     DID
    2.72
     DOES
    2.69
    does
    2.50
    Does
    2.42
     sí
    2.42
    Activations Density 0.125%

    No Known Activations