© 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. 81441
    Prev
    Next
    INDEX
    Explanations

    quantities and counts

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

    This neuron activates on the comma used as a thousands‐grouping separator in large numbers.

    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
     scarcity
    -1.32
     shortage
    -1.23
     abundance
    -1.15
     shortages
    -1.07
     without
    -0.95
    worpen
    -0.91
     lacked
    -0.88
    ˂
    -0.88
     történ
    -0.88
     նաև
    -0.86
    POSITIVE LOGITS
    0
    1.23
     verschillende
    1.02
    спасибо
    1.02
    feliz
    0.90
     diferentes
    0.88
    anhänger
    0.88
    了不少
    0.86
     formação
    0.86
    منم
    0.85
    ケモン
    0.85
    Activations Density 0.028%

    No Known Activations