© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93814
    Prev
    Next
    INDEX
    Explanations

    names: Guy Kawasaki, Guy Clark, Guy Saint-Vil

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

    The neuron strongly activates on occurrences of the capitalized name “Guy.”

    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
     helle
    -0.91
     njia
    -0.79
    ห์
    -0.77
    クリー
    -0.77
     good
    -0.76
    </em>
    -0.75
     excellent
    -0.75
    嵋
    -0.73
     kuan
    -0.73
    过来
    -0.73
    POSITIVE LOGITS
     Guy
    1.25
     Faw
    1.16
    guy
    1.15
     GUY
    1.04
    Guy
    1.01
    liner
    0.98
    laine
    0.93
    elor
    0.88
    ette
    0.85
     Guys
    0.85
    Activations Density 0.010%

    No Known Activations