© 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. 129706
    Prev
    Next
    INDEX
    Explanations

    stationary context

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

    This neuron activates on the word “stationary” (especially when used in technical compound terms like “stationary phase,” “stationary foreground objects,” etc.).

    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
     花纹
    -2.80
    硨
    -2.69
     kredi
    -2.64
    昳
    -2.64
     lancia
    -2.63
    
    -2.61
    푉
    -2.52
    ޏ
    -2.50
     enthou
    -2.48
    ቕ
    -2.48
    POSITIVE LOGITS
    i
    3.30
    m
    2.94
    n
    2.94
    ”
    2.89
    ～　
    2.81
    il
    2.66
     achieving
    2.63
    ).
    2.47
     That
    2.45
    ization
    2.42
    Activations Density 0.004%

    No Known Activations