© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92936
    Prev
    Next
    INDEX
    Explanations

    finance and business terms

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

    The neuron fires on specialized finance and investment terms (e.g., capital, equity, asset, valuation, development) used in business‐oriented contexts.

    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
    不想
    -0.84
     gewähr
    -0.83
    fällig
    -0.82
     jūsų
    -0.80
    Donald
    -0.80
     minum
    -0.78
     rear
    -0.78
     impré
    -0.78
     overall
    -0.78
     easily
    -0.77
    POSITIVE LOGITS
     ambiente
    0.90
    commented
    0.90
     thesis
    0.89
    ntgen
    0.89
     profile
    0.89
    '\\
    0.86
    regime
    0.85
    ем
    0.83
    intensive
    0.83
    класс
    0.82
    Activations Density 0.028%

    No Known Activations