© 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. 59526
    Prev
    Next
    INDEX
    Explanations

    Phillips, Philips, Phillip

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

    This neuron activates on occurrences of the proper name “Philips” or “Phillips.”

    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
    鷓
    -2.77
     肖像
    -2.61
     dichas
    -2.53
    袮
    -2.52
    賒
    -2.48
    鋮
    -2.36
     rivista
    -2.34
    ₰
    -2.33
     appeti
    -2.28
     beendet
    -2.27
    POSITIVE LOGITS
            
    2.95
    و
    2.73
    V
    2.72
    </h6>
    2.70
    </td>
    2.67
         
    2.56
                  
    2.55
    л
    2.50
     são
    2.48
     είναι
    2.45
    Activations Density 0.004%

    No Known Activations