© 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. 84500
    Prev
    Next
    INDEX
    Explanations

    Columbus and associated locations

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

    The neuron is triggered by occurrences of the substring “Columb,” most notably in the place name “Columbus.”

    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
    (',')
    -0.87
    агностика
    -0.82
    Quieres
    -0.82
     seats
    -0.79
    得上
    -0.76
    minaire
    -0.73
    Temporada
    -0.73
    ään
    -0.72
    様
    -0.71
    👝
    -0.71
    POSITIVE LOGITS
     OH
    0.84
    Ohio
    0.81
     Ohio
    0.80
     onely
    0.77
    Amer
    0.71
    Columbus
    0.71
    γραφία
    0.68
     McKinnon
    0.68
    lė
    0.68
    rigger
    0.67
    Activations Density 0.034%

    No Known Activations