© 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. 100284
    Prev
    Next
    INDEX
    Explanations

    west and western locations

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

    The neuron fires on mentions of the westerly direction—tokens like “west” or “western.”

    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
    他们的
    -1.84
    儅
    -1.81
    昪
    -1.77
     también
    -1.74
     הם
    -1.66
     secreto
    -1.65
    自身が
    -1.65
    んび
    -1.64
    褔
    -1.63
    ‘
    -1.62
    POSITIVE LOGITS
     What
    2.02
    k
    1.95
     We
    1.84
    袴
    1.77
    ':
    1.77
     How
    1.77
     и
    1.70
     कई
    1.69
     Consider
    1.68
     جدی
    1.66
    Activations Density 0.048%

    No Known Activations