© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93277
    Prev
    Next
    INDEX
    Explanations

    youth

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

    The neuron strongly activates on occurrences of the word “youth,” especially in organizational names or contexts.

    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
     женщина
    -0.90
     husband
    -0.89
    幼儿园
    -0.87
     kaos
    -0.84
     teka
    -0.83
     הוצ
    -0.81
     hina
    -0.80
     kapa
    -0.79
     disiplin
    -0.79
     butik
    -0.78
    POSITIVE LOGITS
     youth
    3.64
     Youth
    3.09
    Youth
    2.83
    youth
    2.66
     youths
    2.39
     YOUTH
    1.98
     молоде
    1.88
     Jugend
    1.85
    青年
    1.79
     juventud
    1.75
    Activations Density 0.028%

    No Known Activations