© 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. 7088
    Prev
    Next
    INDEX
    Explanations

    linking verbs followed by descriptions

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

    The neuron fires on very high‐frequency/common English words—especially common verbs and function words.

    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
     been
    -1.70
     depuis
    -1.63
     since
    -1.60
     blessure
    -1.52
     accessori
    -1.47
     SINCE
    -1.41
     recentemente
    -1.40
     ตั้ง
    -1.38
    since
    -1.38
    蹿
    -1.38
    POSITIVE LOGITS
     have
    2.31
     has
    1.93
     as
    1.69
    ↵↵
    1.66
     when
    1.61
     Several
    1.55
     classy
    1.54
    when
    1.48
    )।
    1.47
     one
    1.45
    Activations Density 0.247%

    No Known Activations