© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60828
    Prev
    Next
    INDEX
    Explanations

    ranch or farm properties

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

    The neuron fires on mentions of ranch‐related land measurements (e.g. acreage and ranch references, often with numbers).

    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
    ACIÓN
    -1.70
    赑
    -1.66
     uruguay
    -1.61
     iſt
    -1.59
    鈇
    -1.59
     gepubliceerd
    -1.57
     italie
    -1.52
    stalgia
    -1.50
    думы
    -1.48
     polegadas
    -1.45
    POSITIVE LOGITS
     ‘
    1.83
    ,’
    1.79
     “
    1.64
    -
    1.57
    .'”
    1.54
     o
    1.43
     decline
    1.42
     farms
    1.41
    丞
    1.40
    散文
    1.39
    Activations Density 0.026%

    No Known Activations