© 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. 114004
    Prev
    Next
    INDEX
    Explanations

    pertinent questions, systems, issue, measurements, court

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

    The neuron specifically fires for occurrences of the word “pertinent.”

    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
     identité
    -2.75
    }}
    -2.70
     icône
    -2.48
    で
    -2.42
     avec
    -2.41
     énergie
    -2.30
    
    -2.30
     ouverture
    -2.30
    )$.
    -2.20
     supérieures
    -2.20
    POSITIVE LOGITS
    because
    2.80
    ～　
    2.69
     なお
    2.66
     こんな
    2.56
    ﾍ
    2.42
    nę
    2.41
    だけです
    2.34
    塒
    2.34
    って思
    2.33
     ベー
    2.33
    Activations Density 0.002%

    No Known Activations