© 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. 34-GEMMASCOPE-RES-131K
    7. 79381
    Prev
    Next
    INDEX
    Explanations

    grievance procedure

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

    The neuron spotlights numeric expressions—numbers, dates, quantities, monetary amounts, percentages, and other numeric tokens.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     国
    -0.92
     الشعر
    -0.84
     england
    -0.82
    ñez
    -0.81
    \,
    -0.80
    Strategy
    -0.80
     exuber
    -0.80
     HEC
    -0.79
    менте
    -0.79
     SDK
    -0.79
    POSITIVE LOGITS
     grieve
    1.27
     grieved
    1.17
     seniority
    1.17
     grievance
    1.13
     union
    1.06
     grie
    1.05
    grie
    1.03
     Grie
    0.96
    union
    0.91
     bargaining
    0.90
    Activations Density 0.009%

    No Known Activations