© 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. 10-GEMMASCOPE-RES-131K
    7. 12175
    Prev
    Next
    INDEX
    Explanations

    grandmother, grandfather, grandchild

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

    The neuron activates on “grand-” family relationship terms (e.g. grandparent, grandmother, grandchildren, grandchild).

    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
    y
    -2.53
    al
    -2.45
    樒
    -2.42
    黽
    -2.38
    旆
    -2.23
    毉
    -2.23
    皛
    -2.14
     Couple
    -2.09
    la
    -2.05
    是有
    -2.05
    POSITIVE LOGITS
     был
    3.27
     był
    2.89
    vantaged
    2.63
    I
    2.55
    以上です
    2.50
    鸯
    2.33
    というわけで
    2.31
    随后
    2.30
    愎
    2.22
    迨
    2.22
    Activations Density 0.006%

    No Known Activations