© 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. 75365
    Prev
    Next
    INDEX
    Explanations

    names of specific entities

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

    The neuron activates on distinctive proper names and titles—brand names, TV/film titles, product names, chemical or biological entity names, and other unique named entities.

    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
     Mâ
    -1.48
     \&
    -1.41
     Regist
    -1.38
    说说
    -1.36
    ⼭
    -1.31
    ).
    -1.31
    </em>
    -1.30
     Pâ
    -1.30
    '.
    -1.29
    呖
    -1.29
    POSITIVE LOGITS
     have
    1.60
     if
    1.48
     geralmente
    1.42
     powinny
    1.41
     devem
    1.41
     começa
    1.40
     gerçekten
    1.35
     zamiast
    1.34
     czerwony
    1.34
     intentar
    1.34
    Activations Density 0.145%

    No Known Activations