© 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. 82927
    Prev
    Next
    INDEX
    Explanations

    parliamentary assembly legislature house

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

    The neuron chiefly responds to numeric tokens—especially years and other number-based references 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_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
    Stmt
    -0.91
    scalar
    -0.81
    Salad
    -0.77
    ifikationer
    -0.77
     file
    -0.76
     disciplina
    -0.75
    милия
    -0.75
    哒
    -0.74
     pavo
    -0.72
    Эзоҳ
    -0.72
    POSITIVE LOGITS
     Parliament
    4.00
     parliament
    3.88
     legislature
    3.03
    Parliament
    2.94
     Legislature
    2.72
     Congress
    2.69
    parliament
    2.59
     Assembly
    2.41
     House
    2.36
     parli
    2.22
    Activations Density 0.124%

    No Known Activations