© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86533
    Prev
    Next
    INDEX
    Explanations

    meeting people

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

    The neuron activates on phrases about meeting or making new people—i.e. references to encountering or socializing with unfamiliar individuals.

    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
    ↵↵
    -2.41
     you
    -1.78
     two
    -1.30
    ）
    -1.28
     тела
    -1.28
    ↵↵↵↵
    -1.27
    喈
    -1.23
     ristorante
    -1.23
    3
    -1.23
     someone
    -1.21
    POSITIVE LOGITS
     who
    1.85
     estí
    1.43
     bílé
    1.42
    ércio
    1.38
     fonctionnent
    1.38
     whom
    1.34
     cérami
    1.31
    pecabe
    1.30
     různých
    1.30
     Jednak
    1.28
    Activations Density 0.039%

    No Known Activations