© 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. 54100
    Prev
    Next
    INDEX
    Explanations

    US states and laws

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

    The neuron detects mentions of U.S. states or state‐level legal statutes and codes.

    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
     NLRB
    -0.99
    Federal
    -0.91
    鸦
    -0.84
     федера
    -0.84
     federal
    -0.84
    restrial
    -0.79
    ității
    -0.79
    Externé
    -0.77
    伅
    -0.75
     federally
    -0.75
    POSITIVE LOGITS
     Shield
    0.88
     Uniform
    0.88
     False
    0.84
     version
    0.81
     государственной
    0.79
     Little
    0.79
     eaves
    0.78
     shield
    0.78
    vested
    0.77
     state
    0.77
    Activations Density 0.031%

    No Known Activations