© 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. 90825
    Prev
    Next
    INDEX
    Explanations

    Worcestershire and institutions

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

    The neuron principally responds to numeric character sequences (e.g. ages, years, phone numbers, and other multi‐digit numbers).

    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
    ghz
    -0.88
     Mui
    -0.82
     Bolo
    -0.75
     Dolom
    -0.75
    hei
    -0.74
     krab
    -0.73
     Donegal
    -0.72
     dac
    -0.71
    拢
    -0.70
    烹
    -0.70
    POSITIVE LOGITS
     Worcester
    1.93
    Wor
    1.20
     Worcestershire
    1.16
     Malvern
    0.88
    Auburn
    0.85
     Leicester
    0.79
    Birmingham
    0.77
     Birmingham
    0.77
    WOR
    0.73
     Brom
    0.73
    Activations Density 0.011%

    No Known Activations