© 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. 34-GEMMASCOPE-RES-131K
    4. 60355
    Prev
    Next
    INDEX
    Explanations

    remote work

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

    The neuron activates strongly on occurrences of discussing remote work arrangements (e.g. working remotely or from 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_34/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
    ISTER
    -0.88
    lemma
    -0.79
     인스
    -0.77
     OpenCV
    -0.75
    ikkert
    -0.75
    dopodob
    -0.74
    ualitas
    -0.74
    愚
    -0.73
     przeds
    -0.73
     lê
    -0.72
    POSITIVE LOGITS
     remote
    3.94
    remote
    3.36
    Remote
    3.17
     Remote
    3.05
     work
    2.72
     working
    2.59
    REMOTE
    2.58
     remotely
    2.53
     REMOTE
    2.48
    远程
    2.30
    Activations Density 0.178%

    No Known Activations