© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8351
    Prev
    Next
    INDEX
    Explanations

    smart home devices and systems

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

    The neuron strongly activates on references to smart‐home/home‐automation terminology (e.g. “Open Z Wave,” “smart home,” “automation,” “sensors,” etc.).

    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
    ggars
    -1.34
    を獲得
    -1.29
     hvis
    -1.27
     Duitsland
    -1.25
     jemand
    -1.25
    会话
    -1.24
    s
    -1.24
     tandis
    -1.24
     awaited
    -1.22
    żeli
    -1.22
    POSITIVE LOGITS
     about
    1.51
     are
    1.41
    from
    1.23
     volledig
    1.20
     använder
    1.19
     from
    1.18
     your
    1.17
     their
    1.16
     actionTypes
    1.13
     here
    1.12
    Activations Density 0.020%

    No Known Activations