© 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. 64224
    Prev
    Next
    INDEX
    Explanations

    St. Louis references

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

    The neuron is detecting court‐case caption elements—things like party designations (Appellant/Respondent), docket and case numbers, and court names or divisions.

    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
     Taunton
    -0.75
     Urqu
    -0.72
     predeceased
    -0.71
    Tv
    -0.69
     tkinter
    -0.69
    函館
    -0.68
     воздействия
    -0.68
    Խ
    -0.68
    ikou
    -0.68
     चाहिए
    -0.65
    POSITIVE LOGITS
     Missouri
    3.06
    Missouri
    3.03
     STL
    2.11
    STL
    1.90
    stl
    1.71
     Ozark
    1.60
     stl
    1.54
     Cardinals
    1.48
     St
    1.40
     Kirkwood
    1.20
    Activations Density 0.094%

    No Known Activations