© 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. 9091
    Prev
    Next
    INDEX
    Explanations

    directional geographical terms

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

    The neuron detects occurrences of geographic orientation terms (cardinal‐ and intercardinal‐direction words) in place descriptions.

    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
     requerida
    -1.60
    different
    -1.36
     etc
    -1.33
    之类的
    -1.30
    前後
    -1.30
    größern
    -1.28
     ($('#
    -1.26
     ormai
    -1.26
     understandably
    -1.24
     by
    -1.23
    POSITIVE LOGITS
     of
    3.44
     hés
    1.66
     conva
    1.57
     sué
    1.48
     mû
    1.47
     Jika
    1.47
    ┝
    1.45
     délic
    1.41
     parut
    1.39
     seulement
    1.35
    Activations Density 0.056%

    No Known Activations