© 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. 10-GEMMASCOPE-RES-131K
    7. 111435
    Prev
    Next
    INDEX
    Explanations

    Wyoming

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

    This neuron is primarily activated by the word “Wyoming.”

    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
    衚
    -2.86
    '
    -2.66
    >
    -2.48
    遹
    -2.41
    袿
    -2.38
    寕
    -2.36
    他就
    -2.28
    ྵ
    -2.22
    ⟝
    -2.13
     cette
    -2.09
    POSITIVE LOGITS
    缎
    2.38
    𐍆
    2.34
     Wyoming
    2.30
     наша
    2.13
     наш
    1.99
    Wyoming
    1.99
    召喚
    1.98
    鲥
    1.95
     Ни
    1.94
     На
    1.93
    Activations Density 0.005%

    No Known Activations