© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11602
    Prev
    Next
    INDEX
    Explanations

    official appointments and ceremonies

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

    This neuron responds to terms associated with formal induction or oath-taking ceremonies (e.g., “swear in,” “sworn,” “ordain,” “inauguration,” “commissioned”).

    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
     cuyo
    -1.68
     wszystkich
    -1.63
    both
    -1.63
    go
    -1.59
     recounts
    -1.55
    能让
    -1.53
    if
    -1.52
     такого
    -1.52
    do
    -1.49
     lorsqu
    -1.48
    POSITIVE LOGITS
     a
    2.59
     as
    2.17
     at
    2.06
     an
    1.95
     on
    1.84
     in
    1.81
     by
    1.77
     for
    1.58
     kreatif
    1.48
    引言
    1.45
    Activations Density 0.049%

    No Known Activations