© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49252
    Prev
    Next
    INDEX
    Explanations

    American states and territories

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

    The neuron fires on words naming U.S. administrative jurisdictions (states, districts, commonwealths, territories, etc.).

    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
    砧
    -0.78
     EHR
    -0.71
     católica
    -0.70
     consecrated
    -0.69
     CHP
    -0.69
    ℏ
    -0.68
     पू
    -0.67
    熬
    -0.67
    nach
    -0.66
    体制
    -0.66
    POSITIVE LOGITS
     Puerto
    2.05
     territories
    1.89
     Guam
    1.85
    Puerto
    1.71
     Hawaii
    1.64
     Territories
    1.63
    territ
    1.48
     Alaska
    1.40
    Terr
    1.34
     Virgin
    1.30
    Activations Density 0.047%

    No Known Activations