© 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. 78593
    Prev
    Next
    INDEX
    Explanations

    municipal bond advisory

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

    The neuron activates on mentions of municipal‐finance instruments and related bond types (e.g. municipal bonds, RANs, TIFs, tax‐exempt leases, municipal advisory services).

    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
     doté
    -0.87
     myco
    -0.85
    ITAR
    -0.83
    Suerte
    -0.82
     conglomerate
    -0.81
    ⓑ
    -0.80
    dolu
    -0.80
    Quarter
    -0.79
    weder
    -0.78
     metà
    -0.78
    POSITIVE LOGITS
     bond
    1.38
     municipal
    1.08
     bonds
    1.03
    ḗ
    1.02
    牀
    0.96
    官员
    0.94
     Bond
    0.93
    bond
    0.92
     such
    0.91
    baomidou
    0.88
    Activations Density 0.009%

    No Known Activations