© 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. 75989
    Prev
    Next
    INDEX
    Explanations

    U.S. patents

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

    The neuron activates on sequences of digits (numeric tokens), i.e., numbers such as patent or identifier 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
     shared
    -0.95
     only
    -0.93
     probably
    -0.93
     going
    -0.87
     had
    -0.87
     or
    -0.87
     those
    -0.84
     Shared
    -0.82
     frequently
    -0.82
     especially
    -0.81
    POSITIVE LOGITS
     patent
    0.98
     Patent
    0.97
     exuber
    0.96
    patent
    0.95
    σουν
    0.91
    プリ
    0.88
    \}\
    0.86
     NINE
    0.85
    킁
    0.84
    Patent
    0.84
    Activations Density 0.026%

    No Known Activations