© 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. 83902
    Prev
    Next
    INDEX
    Explanations

    childhood to teenage years

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

    The neuron strongly activates on numeric expressions—especially multi‐digit numbers and quantitative ranges (e.g. ages, counts, measurements).

    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
     rojos
    -0.79
     ۲۵
    -0.78
    初心者
    -0.77
    ляю
    -0.77
     ۳۰
    -0.77
    贮
    -0.75
     goles
    -0.75
     verticale
    -0.74
    sill
    -0.74
     blancs
    -0.74
    POSITIVE LOGITS
     teenagers
    3.05
     teenager
    3.00
     teenage
    2.69
     teens
    2.59
     teen
    2.58
     Teen
    2.36
     older
    2.30
    Teen
    2.22
     Teens
    2.11
     adolescents
    2.09
    Activations Density 0.071%

    No Known Activations