© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21167
    Prev
    Next
    INDEX
    Explanations

    understanding of

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

    The neuron strongly activates on occurrences of the word “understanding.”

    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
     Если
    -2.63
     considérons
    -1.99
     ของ
    -1.88
     kompatibel
    -1.80
     Wartawan
    -1.80
    睒
    -1.78
    ☆☆☆☆
    -1.78
    ৳
    -1.75
    cją
    -1.73
     nasıl
    -1.73
    POSITIVE LOGITS
     of
    3.14
     about
    2.16
    {
    2.09
    WAUKEE
    1.91
     that
    1.84
    姈
    1.73
    (“
    1.70
    趼
    1.70
    ⏤
    1.66
    
    1.66
    Activations Density 0.019%

    No Known Activations