© 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. 66451
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific sequences

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

    The neuron selectively responds to numeric tokens (e.g. years, dates, counts, and other digit 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_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
    除此
    -0.85
    Begriffsklä
    -0.84
    他知道
    -0.83
    tidase
    -0.81
     einfach
    -0.81
     try
    -0.79
    落と
    -0.77
     Really
    -0.76
     Consider
    -0.76
    찜
    -0.75
    POSITIVE LOGITS
     mengangg
    0.91
     to
    0.90
     spéciale
    0.88
     pán
    0.87
     respostas
    0.85
    verti
    0.85
    jeje
    0.85
    쳐
    0.85
     pewno
    0.84
    وقال
    0.84
    Activations Density 0.001%

    No Known Activations