© 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. 6804
    Prev
    Next
    INDEX
    Explanations

    stubborn and intractable qualities

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

    The neuron activates on words that denote stubbornness or resistance (e.g., stubborn, recalcitrant, adamant).

    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
     stately
    -1.72
     substantially
    -1.66
    ٨
    -1.66
    !
    -1.63
     sparked
    -1.61
    ٧
    -1.60
     bedeut
    -1.59
     distinctly
    -1.59
    vaní
    -1.57
    ابه
    -1.56
    POSITIVE LOGITS
    橚
    2.09
    
    1.98
    outWeight
    1.91
    不肯
    1.89
     Aunque
    1.88
     hahaha
    1.80
    
    1.79
    
    1.77
    ౭
    1.74
    های
    1.73
    Activations Density 0.016%

    No Known Activations