© 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. 94174
    Prev
    Next
    INDEX
    Explanations

    social interaction and behavior

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

    The neuron fires on words and phrases pertaining to social behavior and interaction.

    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
    izarse
    -0.75
     beroep
    -0.72
    ่วย
    -0.72
     Scritto
    -0.71
    adm
    -0.71
     män
    -0.71
    vereign
    -0.71
     الاقتصاد
    -0.71
    浆
    -0.70
    prised
    -0.69
    POSITIVE LOGITS
     social
    5.13
    social
    4.31
    Social
    3.81
     Social
    3.64
     SOCIAL
    3.55
     socialize
    3.34
    SOCIAL
    3.34
     socialization
    3.31
     sociales
    3.27
     socializing
    3.25
    Activations Density 0.086%

    No Known Activations