© 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. 47273
    Prev
    Next
    INDEX
    Explanations

    District, Municipality, Human Rights

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Ghanaian
    -0.84
     board
    -0.82
     Nigeria
    -0.81
    board
    -0.80
     inqui
    -0.78
    aronne
    -0.78
    >{"
    -0.77
    ClientRect
    -0.77
     quita
    -0.77
     Zimbabwe
    -0.76
    POSITIVE LOGITS
     tricycle
    0.91
     District
    0.82
     district
    0.81
    DISTRICT
    0.78
     Area
    0.75
     Municipality
    0.71
     Districts
    0.70
     Palmerston
    0.69
     assemble
    0.68
     Municipal
    0.68
    Activations Density 0.006%

    No Known Activations