© 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. 104320
    Prev
    Next
    INDEX
    Explanations

    agricultural buildings and storage

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

    The neuron activates on words naming physical outbuildings or storage structures (e.g. barn, shed, coop, hangar, warehouse).

    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
     multifaceted
    -1.50
     sentía
    -1.46
    軼
    -1.41
     currentNode
    -1.40
     stately
    -1.39
    مكن
    -1.34
     Trying
    -1.33
    plas
    -1.30
    when
    -1.30
     fairly
    -1.30
    POSITIVE LOGITS
     passend
    1.44
    \_
    1.41
    ",
    1.41
    "
    1.39
     molte
    1.39
     is
    1.39
    </code>
    1.35
     последние
    1.34
    촉
    1.33
     dando
    1.30
    Activations Density 0.030%

    No Known Activations