© 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. 45306
    Prev
    Next
    INDEX
    Explanations

    businesses and investing

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

    The neuron activates on stock‐market and investment–related terms, including company names, financial metrics (like dividends, revenue, profits), and other trading vocabulary.

    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
    אַ
    -0.77
     Refin
    -0.76
     agate
    -0.75
     CRED
    -0.75
    žete
    -0.74
    大家都
    -0.72
    系数
    -0.72
     fresco
    -0.72
     legato
    -0.72
     Palma
    -0.71
    POSITIVE LOGITS
     businesses
    1.16
     kvalit
    0.98
    Businesses
    0.89
     moat
    0.89
     acheté
    0.88
    franch
    0.88
    cigarette
    0.87
    cellent
    0.86
     quality
    0.85
     automatiques
    0.85
    Activations Density 0.009%

    No Known Activations