© 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. 119614
    Prev
    Next
    INDEX
    Explanations

    home to

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

    The neuron activates on tokens like “home,” “scene,” or “indigenous” when they’re used to say that a place contains, hosts, or is characterized by something (e.g. “X is home to…,” “the scene of…”).

    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
    StoryboardSegue
    -1.53
     управление
    -1.48
     soorten
    -1.43
     ſame
    -1.41
     capuche
    -1.36
    欉
    -1.32
    zonder
    -1.31
    蚍
    -1.31
    lijden
    -1.30
    ccoli
    -1.29
    POSITIVE LOGITS
     preferências
    1.81
    According
    1.80
    ii
    1.75
    了一個
    1.72
     ส์
    1.71
    .”
    1.65
    遢
    1.63
    swire
    1.62
     him
    1.60
    一応
    1.60
    Activations Density 0.007%

    No Known Activations