© 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. 34552
    Prev
    Next
    INDEX
    Explanations

    municipal bonds & financial services

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

    The neuron strongly activates on mentions of financial securities and instruments—especially municipal bonds and related bond types or identifiers.

    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
     PEST
    -0.84
     üblichen
    -0.76
    แผน
    -0.74
    äsche
    -0.73
    عى
    -0.73
     integrados
    -0.72
    tées
    -0.71
    ochemical
    -0.71
     bistro
    -0.71
    กระ
    -0.70
    POSITIVE LOGITS
     corporate
    0.88
    Tries
    0.87
    municip
    0.85
    striped
    0.85
    看了看
    0.81
     STRIP
    0.81
     underlying
    0.80
     Federal
    0.77
    stripped
    0.76
    ัฐ
    0.76
    Activations Density 0.016%

    No Known Activations