© 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. 34-GEMMASCOPE-RES-131K
    7. 59825
    Prev
    Next
    INDEX
    Explanations

    I think or I believe

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

    The neuron strongly activates on occurrences of the first‐person singular pronoun “I.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     assume
    -1.11
     assumption
    -1.03
    probably
    -1.02
     hope
    -0.99
     presumably
    -0.97
     probably
    -0.96
    guess
    -0.96
    assume
    -0.95
     guess
    -0.93
     presume
    -0.92
    POSITIVE LOGITS
     would
    1.56
     wouldn
    1.05
    倾向
    1.03
    Хо
    0.90
    בת
    0.89
     Số
    0.88
    Давайте
    0.88
     lean
    0.87
     ferait
    0.86
     incline
    0.86
    Activations Density 0.030%

    No Known Activations