© 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. 66549
    Prev
    Next
    INDEX
    Explanations

    in memoriam and honor

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

    The neuron responds to expressions of goodwill, blessings, or condolences—especially “May…”-style wishes (e.g. “May his soul rest in peace,” “In loving memory of…”).

    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
     nuova
    -1.41
     tornillos
    -1.39
     químico
    -1.38
     Again
    -1.38
              
    -1.32
     sanitarias
    -1.30
     ponownie
    -1.30
    _-_
    -1.29
     cilindros
    -1.28
    これも
    -1.27
    POSITIVE LOGITS
     canapé
    1.37
     Seigneur
    1.34
     paradis
    1.27
     hommage
    1.27
     occafion
    1.26
     acte
    1.23
    Без
    1.21
    🏢
    1.20
    Vaya
    1.20
     contes
    1.19
    Activations Density 0.021%

    No Known Activations