© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7487
    Prev
    Next
    INDEX
    Explanations

    "I" at start of sentence

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

    The neuron detects occurrences of the standalone first-person pronoun “I.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     люблю
    0.92
     avevo
    0.80
    我现在
    0.78
    хожу
    0.75
    使用了
    0.73
     meinem
    0.71
     मैं
    0.70
    하려고
    0.70
     ഞാൻ
    0.70
    ছিলাম
    0.68
    POSITIVE LOGITS
     fortifications
    0.77
     fortress
    0.66
     briefings
    0.59
     храни
    0.55
    <0xE2>
    0.53
     pihaknya
    0.53
     greater
    0.51
    more
    0.51
     themselves
    0.50
    MORE
    0.50
    Activations Density 0.120%

    No Known Activations