© 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. 84006
    Prev
    Next
    INDEX
    Explanations

    Wisconsin state government

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

    The neuron consistently fires on the word “Wisconsin.”

    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
     near
    -0.81
    nete
    -0.80
     potentially
    -0.76
     позна
    -0.72
     antiqu
    -0.71
    檐
    -0.71
    ᴮ
    -0.70
     specific
    -0.69
     showcasing
    -0.67
     tho
    -0.67
    POSITIVE LOGITS
    Italien
    0.89
     Uw
    0.85
     Savannah
    0.84
     verdienen
    0.82
    PVP
    0.81
    愤
    0.79
     Maddox
    0.79
    ICIAS
    0.79
     Wisconsin
    0.78
    Italy
    0.78
    Activations Density 0.021%

    No Known Activations