© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41552
    Prev
    Next
    INDEX
    Explanations

    younger/elder sibling

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

    The neuron specifically detects the comparative adjective “younger” when used in kinship contexts (e.g. “younger brother/sister”).

    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
    !
    -1.67
     It
    -1.60
     aptly
    -1.44
     This
    -1.41
    aston
    -1.37
     
    -1.34
    ?
    -1.30
     poco
    -1.28
     The
    -1.28
     B
    -1.28
    POSITIVE LOGITS
    s
    1.88
    3
    1.84
     '-';
    1.70
    GRAFIA
    1.67
     settimane
    1.66
     esempi
    1.65
    ECTOS
    1.56
     '*',
    1.52
    UTIONS
    1.50
    饑
    1.50
    Activations Density 0.004%

    No Known Activations