© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45458
    Prev
    Next
    INDEX
    Explanations

    historical topics

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

    The neuron strongly responds to the word “historical” (in any casing), particularly when used as a heading or title.

    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
     การ
    -0.95
     истории
    -0.93
     Piaget
    -0.88
    Ưu
    -0.88
    еро
    -0.85
     calendrier
    -0.83
     língua
    -0.82
     아
    -0.82
     Акаде
    -0.81
    polator
    -0.79
    POSITIVE LOGITS
     perspective
    1.18
     precedent
    1.16
     preservation
    1.08
     periods
    1.05
     context
    1.00
    著名的
    0.96
     period
    0.96
     сложи
    0.95
     landmark
    0.94
    时期
    0.93
    Activations Density 0.022%

    No Known Activations