© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64675
    Prev
    Next
    INDEX
    Explanations

    Edward VI and English history

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

    The neuron is detecting numeric tokens (digits or multi‐digit numbers, such as years, page numbers, or other numeric sequences).

    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
    wg
    -0.84
     REM
    -0.77
     representan
    -0.75
     automática
    -0.74
     Presby
    -0.73
     Ceramics
    -0.73
     CGSize
    -0.71
     Therap
    -0.71
     Mohawk
    -0.71
    
    -0.70
    POSITIVE LOGITS
     England
    1.18
    England
    1.08
    English
    0.93
     English
    0.92
     Tudor
    0.90
    イング
    0.89
    Lady
    0.89
     Lady
    0.84
    english
    0.84
     ENGLISH
    0.81
    Activations Density 0.028%

    No Known Activations