© 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. 60949
    Prev
    Next
    INDEX
    Explanations

    people's names

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

    The neuron fires strongly on personal names (proper nouns) in the text.

    oai_token-act-pair · o4-miniTriggered 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
     then
    -1.57
     essas
    -1.41
    ︲
    -1.39
    这些
    -1.22
    Diese
    -1.20
    this
    -1.20
     داشتن
    -1.19
     memutuskan
    -1.17
    тием
    -1.17
    แล้ว
    -1.17
    POSITIVE LOGITS
     the
    1.35
    恳
    1.19
    最初は
    1.19
    最後は
    1.13
     nắp
    1.12
     nervioso
    1.10
    霁
    1.09
    贏
    1.09
    Lid
    1.09
     what
    1.09
    Activations Density 0.117%

    No Known Activations