© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20346
    Prev
    Next
    INDEX
    Explanations

    two entities interacting

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

    This neuron detects the occurrence of the numeral “two” in 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_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
     acoged
    -1.71
     there
    -1.60
    ↵
    -1.52
    鹚
    -1.46
     cómod
    -1.45
    たまた
    -1.45
    PAIGN
    -1.42
    редиенты
    -1.41
    zzlies
    -1.41
     desarrollar
    -1.40
    POSITIVE LOGITS
     who
    1.54
    ться
    1.54
     themselves
    1.49
    抜群
    1.45
     had
    1.42
     earmarked
    1.40
     rosse
    1.39
    “
    1.39
    スポンサーリンク
    1.38
     marqués
    1.37
    Activations Density 0.013%

    No Known Activations