© 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. 124048
    Prev
    Next
    INDEX
    Explanations

    introducing an example

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

    The neuron is primarily activated by numeric tokens (integers or decimals) 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
    ch
    -1.80
    要
    -1.79
     cucchiaio
    -1.72
    mu
    -1.70
    主要是
    -1.69
     stresses
    -1.68
    ES
    -1.67
    }\
    -1.67
    </b>
    -1.62
    AP
    -1.59
    POSITIVE LOGITS
     például
    1.83
     the
    1.79
    鹩
    1.74
     vergeten
    1.72
    渍
    1.70
    采用了
    1.67
     欣赏
    1.67
     touted
    1.65
    
    1.65
     filósofo
    1.62
    Activations Density 0.009%

    No Known Activations