© 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. 12189
    Prev
    Next
    INDEX
    Explanations

    home and us

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

    The neuron activates on words referring to one’s home or family/household context.

    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
     dezelfde
    -1.55
     latach
    -1.28
     révèle
    -1.27
    ură
    -1.27
     acesta
    -1.27
     verspre
    -1.24
     všetky
    -1.21
     beweging
    -1.21
    Страна
    -1.19
     wijze
    -1.18
    POSITIVE LOGITS
    ).
    1.80
     有
    1.41
    蕻
    1.38
     capitán
    1.36
     dueño
    1.34
     Deel
    1.34
    :
    1.32
    >
    1.30
     dentelle
    1.30
    相当
    1.29
    Activations Density 0.020%

    No Known Activations