© 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. 12666
    Prev
    Next
    INDEX
    Explanations

    surnames

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

    The neuron detects mentions of individual people’s surnames (proper last names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    possessive forms of proper names (surnames followed by apostrophe-s).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of people’s surnames (capitalized last names), especially standalone or in possessive form.

    oai_token-act-pair · gpt-5Triggered 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
     Leah
    0.65
    ☆
    0.64
     Adrián
    0.63
     ühe
    0.63
    ❤️
    0.63
     ৩
    0.61
    💛
    0.61
     passed
    0.61
     Universidade
    0.61
     Apostle
    0.60
    POSITIVE LOGITS
    多彩
    0.60
    VCT
    0.59
    لاین
    0.59
    וב
    0.58
     nond
    0.55
    該
    0.55
     সমিত
    0.54
     plazas
    0.53
    ாண
    0.52
     domicili
    0.52
    Activations Density 0.268%

    No Known Activations