© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59187
    Prev
    Next
    INDEX
    Explanations

    comfort of your home

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

    The neuron fires on prepositional phrases indicating that something happens directly from or in the user’s environment or device (e.g. “from your desktop,” “in your package.json,” “from your mobile device,” “from your home”).

    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
     vogel
    -1.32
    ⮜
    -1.23
    甗
    -1.22
     🤣
    -1.21
    truct
    -1.17
    </h2>
    -1.16
     goud
    -1.16
     😭
    -1.15
     ſ
    -1.14
     خدمة
    -1.14
    POSITIVE LOGITS
     how
    2.03
     what
    1.78
     your
    1.76
     where
    1.61
     with
    1.55
     even
    1.51
     can
    1.46
     within
    1.41
     you
    1.38
     their
    1.38
    Activations Density 0.047%

    No Known Activations