© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4712
    Prev
    Next
    INDEX
    Explanations

    children and youth

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

    This neuron activates on mentions of “children,” essentially detecting when the text refers to children.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decree
    1.02
     fecund
    1.02
     frictionless
    0.90
    Ι
    0.89
     acetylcholine
    0.89
     puck
    0.88
     uncompromising
    0.86
     सटे
    0.86
     indium
    0.85
     doré
    0.84
    POSITIVE LOGITS
    🧒
    1.49
    Children
    1.48
     дошко
    1.47
    儿童
    1.45
     çocuk
    1.38
     الأطفال
    1.36
     dziecka
    1.36
     dzieci
    1.35
     ребенка
    1.32
    幼儿
    1.32
    Activations Density 0.100%

    No Known Activations