© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103151
    Prev
    Next
    INDEX
    Explanations

    Saint Missouri

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

    The neuron strongly activates on legal‐style numeric citations—court reporter volumes, page numbers, docket numbers, and related abbreviations.

    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
    Icy
    -0.83
    連載
    -0.75
    bcm
    -0.73
    Chile
    -0.71
    hastly
    -0.71
    punct
    -0.69
     ؟
    -0.69
    Treas
    -0.68
    porsche
    -0.68
     array
    -0.66
    POSITIVE LOGITS
     Saint
    1.02
     saint
    0.92
     Missouri
    0.90
    Saint
    0.90
    SLP
    0.86
    Missouri
    0.85
     Martinique
    0.84
     Lucia
    0.83
     Pit
    0.82
    ssaint
    0.81
    Activations Density 0.010%

    No Known Activations