© 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. 33484
    Prev
    Next
    INDEX
    Explanations

    another person

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

    The neuron detects words referring to other people or groups (e.g. “other,” “another,” “person,” “people,” “others”).

    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
    ,
    -0.97
      
    -0.90
     fournisseurs
    -0.85
     later
    -0.82
       
    -0.80
    ',
    -0.79
     劇場
    -0.79
     フィット
    -0.78
    แดง
    -0.78
     montagnes
    -0.76
    POSITIVE LOGITS
     people
    1.71
     peoples
    1.48
     lidí
    1.23
     mennesker
    1.20
     ľudí
    1.13
     person
    1.05
    fører
    1.01
    人の
    1.00
     사람
    0.99
     inimes
    0.95
    Activations Density 0.038%

    No Known Activations