© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    millions of entities

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

    The neuron fires on large-scale numeric quantifiers, especially phrasing like “Millions of ….”

    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
     is
    -2.77
    ↵↵
    -2.64
     certaines
    -2.50
     dando
    -2.50
    岨
    -2.45
     zoude
    -2.42
    y
    -2.39
    镲
    -2.38
     overly
    -2.34
     dát
    -2.34
    POSITIVE LOGITS
     multifaceted
    2.83
     During
    2.66
    Both
    2.66
     horrific
    2.63
     frightening
    2.61
     bolster
    2.52
    Despite
    2.45
    Usually
    2.41
     große
    2.36
    嬗
    2.36
    Activations Density 0.016%

    No Known Activations