© 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. 54056
    Prev
    Next
    INDEX
    Explanations

    numbers following 5 or five

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

    The neuron activates on standalone numeric tokens (i.e. numbers) 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
    {
    -1.38
    仅
    -1.07
    </b>
    -1.06
     nevertheless
    -1.05
    mbps
    -1.04
    ๖
    -1.03
     Jüng
    -1.03
     thirds
    -1.02
    ../../
    -1.01
     Müll
    -0.98
    POSITIVE LOGITS
    Jahres
    1.43
    ܆
    1.38
     dezen
    1.30
     مستوى
    1.27
     olika
    1.24
    鸸
    1.19
    ousine
    1.17
    
    1.17
    tizing
    1.16
    ñe
    1.16
    Activations Density 0.272%

    No Known Activations