© 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. 60463
    Prev
    Next
    INDEX
    Explanations

    Cleveland and its associations

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

    The neuron detects occurrences of the proper noun “Cleveland.”

    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
    珍
    -1.00
    Tus
    -0.86
    shelter
    -0.84
     정
    -0.84
    cw
    -0.83
    Amer
    -0.81
    Tas
    -0.81
     RUB
    -0.80
     dc
    -0.79
    १
    -0.79
    POSITIVE LOGITS
    rões
    1.05
    misión
    0.93
    avond
    0.93
     CLE
    0.92
    rugada
    0.91
     spelen
    0.90
     Clinic
    0.90
     hő
    0.90
    само
    0.89
     clever
    0.88
    Activations Density 0.006%

    No Known Activations