© 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. 42459
    Prev
    Next
    INDEX
    Explanations

    selling or renting your home

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

    The neuron activates on numeric expressions—digits, decimals, and percentages—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_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
    ↵
    -2.97
     &
    -2.14
     we
    -2.05
    5
    -1.93
    大多
    -1.93
    要在
    -1.91
    t
    -1.87
    O
    -1.85
     serán
    -1.84
     tienen
    -1.84
    POSITIVE LOGITS
    獁
    2.41
    Недостатки
    2.17
    縺
    2.14
    ândia
    2.11
    ҂
    2.06
    鯪
    2.06
    妪
    1.94
    桖
    1.91
     Ordre
    1.90
     Yeni
    1.88
    Activations Density 0.159%

    No Known Activations