© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6319
    Prev
    Next
    INDEX
    Explanations

    Western geographic direction or concepts

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

    The neuron is a high‐precision detector for the capitalized word “West.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ટ
    0.64
     রাষ্ট্রপতি
    0.57
    Dare
    0.55
     Dare
    0.54
    тину
    0.54
    Labeled
    0.52
    Lab
    0.52
    ୋ
    0.52
     Motion
    0.52
     काळ
    0.51
    POSITIVE LOGITS
    इंडीज
    0.95
    falen
    0.81
    coast
    0.79
    WEST
    0.77
     Indies
    0.77
    inghouse
    0.76
    cott
    0.73
     coast
    0.72
     WEST
    0.71
     COAST
    0.71
    Activations Density 0.135%

    No Known Activations