© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 906
    Prev
    Next
    INDEX
    Explanations

    you can/could/must

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

    The neuron activates on second-person addresses—instances of “you” (and its capitalized form) directly speaking to the reader.

    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
    aughters
    0.78
    σουμε
    0.74
     ourselves
    0.72
    umuza
    0.70
     tirelessly
    0.67
    ours
    0.66
    aughter
    0.65
    artig
    0.64
    ender
    0.63
    unjung
    0.61
    POSITIVE LOGITS
     می‌توانید
    0.86
     možete
    0.85
     pueden
    0.84
    可以通过
    0.82
     Dapat
    0.82
     podem
    0.81
    可以使用
    0.81
     dapat
    0.80
     lahko
    0.80
     يمكن
    0.79
    Activations Density 0.093%

    No Known Activations