© 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. 25870
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and punctuation

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

    This neuron detects numeric tokens (numbers and decimal values).

    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
     семь
    -0.88
     Nineteen
    -0.87
     Espíritu
    -0.80
    竊
    -0.80
     حدود
    -0.80
    ઐ
    -0.80
    ۱۷
    -0.78
     Patti
    -0.77
     девя
    -0.77
    🧿
    -0.76
    POSITIVE LOGITS
     causes
    0.85
    からね
    0.85
     ten
    0.78
    рах
    0.76
     transmettre
    0.74
     bun
    0.70
    村民
    0.68
    著名的
    0.68
    หา
    0.67
     things
    0.66
    Activations Density 0.072%

    No Known Activations