© 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. 10-GEMMASCOPE-RES-131K
    7. 98831
    Prev
    Next
    INDEX
    Explanations

    would be + [action]

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

    The neuron fires strongly on modal-auxiliary constructions indicating future or conditional events—especially phrases built around “would be.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    تفسير
    -1.21
     daar
    -1.20
     たい
    -1.16
    根据
    -1.16
    Menurut
    -1.16
    樵
    -1.13
    sidian
    -1.10
    кать
    -1.10
    tığı
    -1.09
     ваших
    -1.06
    POSITIVE LOGITS
     was
    1.47
     last
    1.41
     "
    1.32
    ffiche
    1.20
    おわりに
    1.16
     endregion
    1.16
     fotó
    1.16
     fenêtres
    1.16
    という感じ
    1.13
    </b>
    1.12
    Activations Density 0.060%

    No Known Activations