© 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. 113543
    Prev
    Next
    INDEX
    Explanations

    meeting with people or groups

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

    The neuron detects mentions of someone “meeting with” or “meeting” another person or group.

    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
    ostomy
    -2.08
    His
    -1.90
     sorgfäl
    -1.84
     которое
    -1.83
     当
    -1.77
    鞭
    -1.76
     有
    -1.73
    </h2>
    -1.73
    unikasi
    -1.69
     suhu
    -1.69
    POSITIVE LOGITS
    嗞
    1.81
     unga
    1.78
     vaqueros
    1.72
    勠
    1.71
     ï
    1.70
     kimdir
    1.66
     kazak
    1.65
    RemindMe
    1.63
     fundas
    1.60
    ㌘
    1.59
    Activations Density 0.009%

    No Known Activations