© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16174
    Prev
    Next
    INDEX
    Explanations

    living spaces

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

    The neuron activates on mentions of the living space (e.g. “living room” or “living area”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ИС
    0.86
    quam
    0.85
     succinctly
    0.84
     concisely
    0.79
    SOM
    0.78
    {
    0.77
    e
    0.77
    ล
    0.77
    ্ড
    0.75
     strollers
    0.74
    POSITIVE LOGITS
     وإ
    0.91
     până
    0.91
    dwelling
    0.90
     முறை
    0.86
     exo
    0.85
     uống
    0.84
    َة
    0.83
     இருவரும்
    0.83
    ⁄
    0.83
     şi
    0.82
    Activations Density 0.004%

    No Known Activations