© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7451
    Prev
    Next
    INDEX
    Explanations

    New York City neighborhoods

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

    The neuron activates on mentions of specific New York City neighborhood or district names.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -2.78
    If
    -2.09
    4
    -2.02
    They
    -1.77
    𔘓
    -1.76
    Never
    -1.75
    Maybe
    -1.70
    Not
    -1.66
    Might
    -1.63
    兩個
    -1.63
    POSITIVE LOGITS
     So
    1.82
     deteriorating
    1.59
     heighten
    1.59
    
    1.59
     ominous
    1.55
     precarious
    1.53
    中毒
    1.52
    tego
    1.51
     Поэтому
    1.50
     Vorsitzender
    1.49
    Activations Density 0.011%

    No Known Activations