© 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. 64473
    Prev
    Next
    INDEX
    Explanations

    regular expression components

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

    The neuron is keyed to spotting numeric characters—particularly digits used within regex or code patterns.

    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
     in
    -0.96
     bernama
    -0.93
     !}
    -0.91
    ']}
    -0.89
    .*")]
    -0.88
    змом
    -0.87
     during
    -0.86
    ']]
    -0.84
    %">
    -0.83
    ⍨
    -0.83
    POSITIVE LOGITS
    為に
    0.94
    collating
    0.84
     plusieurs
    0.83
     علاوه
    0.81
    numb
    0.81
    除了
    0.80
    是一種
    0.79
     antigos
    0.79
    是一個
    0.79
     geko
    0.79
    Activations Density 0.012%

    No Known Activations