© 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. 118365
    Prev
    Next
    INDEX
    Explanations

    phone numbers and place names

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

    The neuron activates on isolated numeric digits 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_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
    😵
    -1.00
    ⌊
    -0.91
     their
    -0.89
    ⌈
    -0.89
     Meille
    -0.89
    вшего
    -0.86
     mikro
    -0.86
    🤯
    -0.86
    🤓
    -0.86
    ฿
    -0.85
    POSITIVE LOGITS
    mopol
    0.90
    2
    0.88
    fasis
    0.88
     debate
    0.87
     aforementioned
    0.87
    acidade
    0.86
     smuggled
    0.86
    ディズニー
    0.84
     repatriation
    0.84
    3
    0.81
    Activations Density 0.003%

    No Known Activations