© 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. 22-GEMMASCOPE-RES-131K
    7. 16560
    Prev
    Next
    INDEX
    Explanations

    New Jersey

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

    The neuron consistently activates on mentions of New Jersey place names (e.g., “New Jersey,” “Montville,” “Hudson County”).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </u>
    -1.88
    </h3>
    -1.84
    </strong>
    -1.67
    </i>
    -1.45
     “
    -1.44
     ornate
    -1.43
     –
    -1.41
     aussi
    -1.39
     gering
    -1.33
    seiko
    -1.33
    POSITIVE LOGITS
     XXVII
    1.67
    NJ
    1.55
     nj
    1.52
    льники
    1.52
     XXXV
    1.50
     maksi
    1.48
    ước
    1.46
    يلة
    1.45
     NJ
    1.44
     comunale
    1.44
    Activations Density 0.029%

    No Known Activations