© 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. 34-GEMMASCOPE-RES-131K
    7. 108749
    Prev
    Next
    INDEX
    Explanations

    welcoming someone to an event

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

    The neuron preferentially activates on personal-relationship and audience-address terms—kinship words (e.g. “family,” “friends”) and inclusive pronouns (“we,” “my,” “you”) used in speech.

    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
     тогда
    -1.38
     THEN
    -1.19
    middels
    -1.08
    Meanwhile
    -1.06
    defin
    -1.05
    
    -1.04
    詆
    -0.98
     akkor
    -0.98
    latest
    -0.96
     Meanwhile
    -0.96
    POSITIVE LOGITS
     tonight
    2.25
     today
    1.98
     your
    1.87
     here
    1.81
     you
    1.63
     yourselves
    1.54
     this
    1.30
     Tonight
    1.30
     standing
    1.20
     aanwezig
    1.19
    Activations Density 0.038%

    No Known Activations