© 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. 19640
    Prev
    Next
    INDEX
    Explanations

    sibling relationships

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

    This neuron strongly activates on the word “siblings,” i.e. it detects mentions of that specific family-relationship term.

    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
    ↵
    -2.69
     {
    -2.44
    ты
    -2.36
    诳
    -2.36
     had
    -2.34
    к
    -2.09
    ט
    -2.05
     went
    -2.03
    </strong>
    -2.00
    倥
    -1.98
    POSITIVE LOGITS
    C
    2.59
    ,/
    2.52
    5
    2.48
    n
    2.47
    Alongside
    2.45
    쩡
    2.42
    ﱠ
    2.42
    咴
    2.33
     Thus
    2.28
     Когда
    2.25
    Activations Density 0.002%

    No Known Activations