© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13822
    Prev
    Next
    INDEX
    Explanations

    Gerald Ford; US Presidents with heights

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

    The neuron activates specifically on the proper name “Gerald.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     프
    0.61
     Majority
    0.58
     Cassie
    0.57
    ুলের
    0.56
    तार
    0.56
     本当
    0.55
     Kayla
    0.55
    ++++++++++++++++
    0.55
     تنظیم
    0.55
     Cait
    0.53
    POSITIVE LOGITS
     sovere
    0.64
    aths
    0.61
    owered
    0.60
    eteries
    0.58
    langs
    0.57
     spacious
    0.57
     corpo
    0.57
    abei
    0.56
    anguages
    0.55
    abody
    0.55
    Activations Density 0.000%

    No Known Activations