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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82420
    Prev
    Next
    INDEX
    Explanations

    states and abbreviations

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

    The neuron detects numeric U.S. postal (ZIP) codes embedded in address lines.

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

    No Comments

    Negative Logits
    艙
    -0.82
    isfile
    -0.79
    ®.
    -0.78
    觀察
    -0.78
     Verbindungen
    -0.78
    dö
    -0.76
    得到
    -0.75
    ：「
    -0.75
     bezeich
    -0.74
     Übergang
    -0.74
    POSITIVE LOGITS
     QLD
    1.42
     TX
    1.22
     NY
    1.17
     NJ
    1.06
    TX
    1.06
     CA
    1.02
     MN
    1.02
     NSW
    1.02
     TN
    0.98
     штат
    0.98
    Activations Density 0.035%

    No Known Activations