© 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. 10-GEMMASCOPE-RES-131K
    7. 75038
    Prev
    Next
    INDEX
    Explanations

    on days or months

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

    This neuron lights up primarily on numeric tokens—especially digits in dates, times, and other number expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    zembro
    -1.74
     by
    -1.66
    Educación
    -1.59
    騫
    -1.55
    футболка
    -1.54
     vergeten
    -1.54
     okru
    -1.52
    
    -1.52
    ﮩ
    -1.51
    先に
    -1.50
    POSITIVE LOGITS
     –
    2.06
    .
    2.03
    ll
    1.78
    —
    1.77
     The
    1.77
    ↵↵
    1.73
    7
    1.63
     что
    1.61
    l
    1.59
    <h2>
    1.58
    Activations Density 0.005%

    No Known Activations