© 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. 10-GEMMASCOPE-RES-131K
    7. 9696
    Prev
    Next
    INDEX
    Explanations

    I don't think

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

    The neuron consistently activates on occurrences of the word “think.”

    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
     jesús
    -2.06
    Уже
    -2.03
     relentlessly
    -1.99
     touted
    -1.98
    滙
    -1.93
     欣赏
    -1.88
     北市
    -1.84
     leopardo
    -1.80
     Fällen
    -1.79
     supplémentaire
    -1.79
    POSITIVE LOGITS
    {
    2.64
     anc
    2.05
    li
    2.02
     la
    1.85
    2
    1.83
    和小
    1.77
    ":
    1.72
    ():
    1.70
    萏
    1.69
     woon
    1.67
    Activations Density 0.008%

    No Known Activations