© 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. 22-GEMMASCOPE-RES-131K
    7. 35796
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    The neuron is activated by numeric tokens (digits or numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     for
    -1.23
     StringIO
    -1.00
     Due
    -0.98
    ってしまった
    -0.96
    みてください
    -0.93
     these
    -0.92
     arkiv
    -0.88
    SeekBar
    -0.87
     kado
    -0.87
    orge
    -0.85
    POSITIVE LOGITS
     couronne
    1.02
     proberen
    0.96
    なに
    0.95
    私に
    0.93
     Immigrant
    0.92
    基本的に
    0.91
    . 
    0.91
    なかな
    0.91
    끝
    0.90
     також
    0.90
    Activations Density 0.001%

    No Known Activations