© 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. 10-GEMMASCOPE-RES-131K
    7. 19369
    Prev
    Next
    INDEX
    Explanations

    introducing people or things to meet

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

    This neuron detects “Meet” headlines or similar introductory cues that introduce a 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
     then
    -1.48
     Wissenschaften
    -1.37
    hline
    -1.31
     that
    -1.29
    infty
    -1.28
     shutter
    -1.23
    isitions
    -1.20
     sowas
    -1.20
     you
    -1.17
     losses
    -1.17
    POSITIVE LOGITS
     our
    1.67
     a
    1.41
     tuta
    1.31
    Zdrav
    1.30
    Vendredi
    1.27
     kimdir
    1.27
     हमारे
    1.26
    還有
    1.26
     cerveza
    1.24
    Другие
    1.21
    Activations Density 0.053%

    No Known Activations