© 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. 119370
    Prev
    Next
    INDEX
    Explanations

    finance Officer, Minister, team

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

    The neuron fires on occurrences of the word “finance,” especially when it appears as a heading or prominent term 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
     diversas
    -0.98
    categorias
    -0.94
     formally
    -0.94
     reliably
    -0.93
     referenced
    -0.92
     differing
    -0.91
     devised
    -0.90
     suficientes
    -0.90
     inadvertently
    -0.90
    pastebin
    -0.90
    POSITIVE LOGITS
    ⛦
    1.02
    маз
    0.97
     ministers
    0.95
    гот
    0.94
     voitures
    0.93
    utama
    0.93
     нарко
    0.93
     табле
    0.91
    🛈
    0.90
     côtés
    0.90
    Activations Density 0.008%

    No Known Activations