© 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. 34-GEMMASCOPE-RES-131K
    4. 25586
    Prev
    Next
    INDEX
    Explanations

    names, places, and events

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

    The neuron is primarily triggered by numeric tokens (multi‐digit numbers, dates, counts, etc.).

    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
     Intro
    -0.77
     ple
    -0.72
     Mangel
    -0.71
    卡片
    -0.71
     косме
    -0.70
    aha
    -0.68
     print
    -0.68
     Duran
    -0.67
     ja
    -0.66
     pine
    -0.65
    POSITIVE LOGITS
     discography
    0.80
     brome
    0.79
     tunic
    0.78
     penjelasan
    0.76
    "]="
    0.76
     JES
    0.73
    zmm
    0.73
    getForm
    0.73
     fung
    0.72
     exud
    0.72
    Activations Density 0.024%

    No Known Activations