© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12345
    Prev
    Next
    INDEX
    Explanations

    Peter and Pierre names

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

    This neuron responds specifically to occurrences of the proper name “Peter.”

    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_31_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
    髻
    0.72
    motor
    0.61
    mode
    0.59
    military
    0.56
    LocalDateTime
    0.55
    近年来
    0.55
    Goods
    0.54
    List
    0.54
    pepper
    0.54
    list
    0.54
    POSITIVE LOGITS
     Độ
    0.65
    坝
    0.61
    buri
    0.59
    ড়ী
    0.57
    öm
    0.57
    öy
    0.56
    ᡳ
    0.56
    ෙන්
    0.55
     Debye
    0.55
     entweder
    0.55
    Activations Density 0.030%

    No Known Activations