© 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. 10-GEMMASCOPE-RES-131K
    7. 3648
    Prev
    Next
    INDEX
    Explanations

    Churchill, Winston, Winnie, Richie

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

    The neuron selectively activates on the name “Churchill” (often splitting into “Church” + “ill”) and on the given name “Winston,” i.e. it’s detecting occurrences of “Winston Churchill.”

    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
    
    -2.69
    纐
    -2.48
    -'
    -2.31
    嚳
    -2.27
    
    -2.19
    ldots
    -2.16
    ⸫
    -2.16
    떳
    -2.14
     biela
    -2.14
     consecutive
    -2.09
    POSITIVE LOGITS
    ate
    2.88
    </i>
    2.36
     If
    2.33
    which
    2.23
     This
    2.20
    人們
    2.17
    is
    2.13
     You
    2.08
    what
    2.06
    to
    1.98
    Activations Density 0.002%

    No Known Activations