© 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. 69284
    Prev
    Next
    INDEX
    Explanations

    east and related directions

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

    The neuron detects mentions of compass directions (e.g. “east,” “southward,” “west,” etc.) in geographic contexts.

    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
    ’
    -2.88
    .
    -2.08
     “
    -2.08
     a
    -1.87
     haupts
    -1.84
    ”
    -1.82
    .”
    -1.81
    —“
    -1.79
    に行きました
    -1.75
     freundlichen
    -1.73
    POSITIVE LOGITS
    鹮
    2.22
    隄
    1.98
    цію
    1.96
     are
    1.96
     Accessoires
    1.95
    に
    1.90
     brille
    1.84
    ጢ
    1.83
    VERTISEMENT
    1.81
    瑱
    1.81
    Activations Density 0.045%

    No Known Activations