© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71666
    Prev
    Next
    INDEX
    Explanations

    Murphy surname

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

    The neuron specifically activates on occurrences of the proper name “Murphy.”

    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
     astonishing
    -2.58
    
    -2.58
    
    -2.47
     need
    -2.45
     perfetto
    -2.30
    pherals
    -2.25
    ers
    -2.23
     encyclo
    -2.22
    er
    -2.20
    ,"
    -2.19
    POSITIVE LOGITS
    <bos>
    2.42
    禵
    2.39
    But
    2.20
     voordat
    2.20
     vanwege
    2.19
    寘
    2.17
    嗚
    2.08
          
    2.06
    いいのか
    2.06
    </td>
    2.05
    Activations Density 0.001%

    No Known Activations