© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18890
    Prev
    Next
    INDEX
    Explanations

    western directions

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

    a location/tourist-place detector that activates on place names and mentions of cities, districts, or landmarks in travel itinerary text.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Восто
    0.49
     Southeastern
    0.47
     Northeastern
    0.41
     восто
    0.41
    मिनी
    0.41
     Đông
    0.40
    東北
    0.40
    赣
    0.40
     Eastern
    0.40
    southeast
    0.39
    POSITIVE LOGITS
     western
    0.87
     غرب
    0.81
    western
    0.79
     westward
    0.79
     Western
    0.79
    西
    0.78
     WEST
    0.77
     west
    0.77
     запад
    0.76
     पश्चिमी
    0.75
    Activations Density 0.045%

    No Known Activations