© 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. 15779
    Prev
    Next
    INDEX
    Explanations

    Good followed by names

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

    This neuron activates on the capitalized word “Good.”

    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
     aksesuar
    -2.50
    ↵
    -2.45
     originalen
    -2.39
     logró
    -2.30
     mutfak
    -2.28
    とても
    -2.22
     interconnected
    -2.20
    ほんと
    -2.17
     baskılı
    -2.14
     französische
    -2.14
    POSITIVE LOGITS
     was
    2.91
    a
    2.80
    呓
    2.52
     knows
    2.34
    していました
    2.33
    霂
    2.25
    ？！”
    2.25
    های
    2.20
    胧
    2.20
    itemBuilder
    2.17
    Activations Density 0.007%

    No Known Activations