© 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. 31167
    Prev
    Next
    INDEX
    Explanations

    financial offerings and IPOs

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

    This neuron detects mentions of municipal finance terms, especially “Municipal Bonds” and related bond transactions.

    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
     Abbas
    -0.73
    etsch
    -0.71
     tils
    -0.71
    ἢ
    -0.69
    vedev
    -0.69
     przecież
    -0.69
    ژ
    -0.69
    ઉ
    -0.69
    ਤ
    -0.69
     Sailor
    -0.68
    POSITIVE LOGITS
     underwriting
    2.42
     lead
    1.44
     syndicate
    1.30
    Under
    1.28
    lead
    1.27
     Under
    1.24
    Lead
    1.10
     syndic
    1.08
     Underworld
    1.03
     Lead
    0.96
    Activations Density 0.015%

    No Known Activations