© 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. 10-GEMMASCOPE-RES-131K
    7. 67728
    Prev
    Next
    INDEX
    Explanations

    children's content nouns

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

    The neuron fires on references to “children’s” content—that is, when the text mentions children’s books, music, projects, 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_10/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
    𓐍
    -2.45
    鲼
    -2.20
    嫫
    -2.11
    籥
    -1.99
    逦
    -1.99
    薷
    -1.98
     was
    -1.88
     continue
    -1.88
    tagHelper
    -1.88
    𓁹
    -1.87
    POSITIVE LOGITS
    0
    2.41
    ).
    2.17
    9
    2.08
     تھے
    2.05
     تھا
    2.02
     feiner
    1.99
     häufiger
    1.97
     zuhause
    1.95
    {
    1.93
     meisten
    1.90
    Activations Density 0.008%

    No Known Activations