© 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. 12973
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

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

    This neuron activates on personal pronouns (esp. first‐ and second‐person “I”/“you” words) across languages.

    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
    0.67
     />
    0.64
     dast
    0.63
     çeşitli
    0.63
     veya
    0.62
     werd
    0.62
    ↵↵↵
    0.61
     event
    0.61
     pelaksanaan
    0.61
     tiki
    0.61
    POSITIVE LOGITS
    들은
    0.93
    們
    0.84
    들도
    0.83
    们的
    0.79
    也都
    0.75
     cũng
    0.74
    ก็จะ
    0.67
    已經
    0.67
     всегда
    0.66
     уже
    0.66
    Activations Density 0.005%

    No Known Activations