© 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. 34-GEMMASCOPE-RES-131K
    7. 83917
    Prev
    Next
    INDEX
    Explanations

    Bart names and company identifiers

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

    The neuron strongly activates on uppercase tokens that are part of headings or titles—especially names and entities (e.g. case‐party names, author names, or institutional names) in legal and bibliographic sections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Flux
    -0.76
     Move
    -0.75
    PRISE
    -0.74
     proved
    -0.72
    Move
    -0.72
    |@
    -0.70
    ]}{
    -0.69
     visitar
    -0.68
     CRM
    -0.68
    ,\,\
    -0.68
    POSITIVE LOGITS
    ᐳ
    0.79
    ču
    0.77
    때
    0.77
     COLON
    0.76
     aconte
    0.76
    条款
    0.75
     обез
    0.75
     analisar
    0.75
     cabelos
    0.73
    ᱾
    0.73
    Activations Density 0.021%

    No Known Activations