© 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. 110986
    Prev
    Next
    INDEX
    Explanations

    numbers and Docket No

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

    The neuron detects multi‐digit numerical tokens (e.g. long numbers and citation/page references).

    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
     getRandom
    -0.81
    Opéra
    -0.80
     biais
    -0.79
    ربه
    -0.75
    zī
    -0.73
    Kita
    -0.73
    ผ่าน
    -0.73
    WeChat
    -0.72
    ÉL
    -0.71
     Travail
    -0.71
    POSITIVE LOGITS
     lines
    0.81
    ↵↵↵
    0.79
               
    0.79
    vand
    0.79
     vows
    0.79
              
    0.78
    ‖
    0.77
                   
    0.76
    shl
    0.75
     Besonder
    0.74
    Activations Density 0.003%

    No Known Activations