© 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. 10979
    Prev
    Next
    INDEX
    Explanations

    other, others, autres

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

    The neuron fires on numeric tokens—any isolated numbers or digit‐containing strings 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
     by
    -1.13
     jego
    -1.01
     его
    -0.90
    ته
    -0.88
     обувь
    -0.88
     już
    -0.85
     its
    -0.83
    樑
    -0.82
     sebagai
    -0.82
    
    -0.80
    POSITIVE LOGITS
     other
    1.03
    шой
    0.99
    olische
    0.93
     autres
    0.93
    isés
    0.91
     anderen
    0.91
     aident
    0.90
    other
    0.89
     coucher
    0.88
     інших
    0.87
    Activations Density 0.041%

    No Known Activations