© 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. 3402
    Prev
    Next
    INDEX
    Explanations

    you can

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

    The neuron strongly activates on the pronoun “you” when it’s used to directly address or exhort the reader (e.g. in ad-style “You will…” statements).

    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
    iciency
    0.64
    бліоте
    0.64
    会儿
    0.61
    꿨
    0.61
     contigo
    0.59
     ګرځ
    0.59
    σουμε
    0.58
    ॓
    0.57
    よかった
    0.56
    ிருந்தது
    0.56
    POSITIVE LOGITS
     pueden
    0.80
     can
    0.77
     Dapat
    0.71
     môžu
    0.70
     puede
    0.69
     needn
    0.67
     μπορεί
    0.67
    can
    0.66
     môže
    0.66
    te
    0.65
    Activations Density 0.192%

    No Known Activations