© 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. 22-GEMMASCOPE-RES-131K
    7. 15936
    Prev
    Next
    INDEX
    Explanations

    boston, massachusetts, circuit

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

    The main thing this neuron does is pick out legal case citation elements (e.g. the “X vs. Y,” volume numbers, reporter abbreviations, dates, and related punctuation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     playmobil
    -1.00
     snak
    -0.98
     学習
    -0.97
     geforce
    -0.97
     Cleopatra
    -0.96
     
    -0.94
     RIO
    -0.94
     vedno
    -0.94
     doos
    -0.93
     damas
    -0.93
    POSITIVE LOGITS
     Massachusetts
    1.91
     Boston
    1.74
    Massachusetts
    1.59
    Boston
    1.46
    BOSTON
    1.43
     Harvard
    1.21
     MIT
    1.19
    boston
    1.15
     his
    1.14
     Cambridge
    1.13
    Activations Density 0.034%

    No Known Activations