© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65787
    Prev
    Next
    INDEX
    Explanations

    proper names, often followed by titles

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

    This neuron detects personal proper names (people’s names).

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

    capitalized proper names and other named entities (people, places, organizations/events).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the name "Brock" or words starting with "Brock".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -3.09
    )
    -2.64
    or
    -2.58
    ри
    -2.53
    ...
    -2.52
    ਃ
    -2.48
    ти
    -2.45
     ´
    -2.39
    <strong>
    -2.36
    би
    -2.36
    POSITIVE LOGITS
    ৄ
    2.98
    ☫
    2.91
    囖
    2.80
    拶
    2.72
    งิน
    2.70
    鼕
    2.64
    苙
    2.63
    鲣
    2.61
    桄
    2.58
    是吗
    2.56
    Activations Density 0.049%

    No Known Activations