© 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. 22-GEMMASCOPE-RES-131K
    7. 66371
    Prev
    Next
    INDEX
    Explanations

    boundary condition

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

    This neuron activates on mentions of “boundary conditions” (including specific types like Neumann, Robin, periodic, etc.) in technical or mathematical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    werf
    -1.19
     réessayer
    -1.10
    Demografie
    -1.09
    ⼥
    -1.05
     estrutura
    -1.05
     především
    -1.04
    
    -1.04
     käyttää
    -1.03
    晤
    -1.02
    beste
    -1.01
    POSITIVE LOGITS
     on
    1.57
     for
    1.40
    硕士
    1.02
     at
    1.00
     आहे
    0.98
     ČR
    0.97
     akzeptieren
    0.94
    பு
    0.94
     WHAT
    0.94
     zulassen
    0.91
    Activations Density 0.020%

    No Known Activations