© 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. 81320
    Prev
    Next
    INDEX
    Explanations

    Anton and antonyms

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

    The neuron specifically fires on the proper name “Anton.”

    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
    izziness
    -0.81
    黽
    -0.80
     ત
    -0.75
    usnya
    -0.75
    volante
    -0.75
    目錄
    -0.74
    ílica
    -0.71
    ventil
    -0.70
     Schwab
    -0.70
     除
    -0.70
    POSITIVE LOGITS
     чехол
    0.81
    uniform
    0.79
    ín
    0.79
    ucci
    0.77
    絶対
    0.72
    希望能
    0.72
    trans
    0.72
     enorme
    0.71
    Unexpected
    0.71
    hydra
    0.70
    Activations Density 0.014%

    No Known Activations