© 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. 70323
    Prev
    Next
    INDEX
    Explanations

    proper nouns, titles, and names

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

    The neuron detects individual proper names, especially surnames—i.e., mentions of people’s names.

    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
    ⦊
    -1.52
     klima
    -1.39
     praktis
    -1.37
    Disciplina
    -1.35
    Origem
    -1.31
    Сі
    -1.31
    逡
    -1.30
    Privat
    -1.29
    ivable
    -1.29
    κτή
    -1.26
    POSITIVE LOGITS
    ent
    1.26
    -
    1.23
     who
    1.22
     kennt
    1.18
    指示
    1.18
    得
    1.17
     haven
    1.16
    在
    1.14
    _
    1.13
    でしたが
    1.13
    Activations Density 0.071%

    No Known Activations