© 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. 82622
    Prev
    Next
    INDEX
    Explanations

    financial + context

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

    The neuron activates on finance‐related terms (e.g. “financial,” “financially,” “financing”).

    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
     服务
    -0.87
     enthusi
    -0.87
    ivät
    -0.86
     Enkel
    -0.84
     pagare
    -0.81
     тари
    -0.80
    rejected
    -0.80
    предели
    -0.79
    𓆟
    -0.78
     hek
    -0.78
    POSITIVE LOGITS
     resources
    1.29
     support
    1.16
     constraints
    1.15
    resources
    1.02
     worries
    1.01
     aspects
    1.00
     assistance
    0.99
    ̯
    0.98
     aspect
    0.96
     transactions
    0.95
    Activations Density 0.016%

    No Known Activations