© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    travelers, locals, users

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

    The neuron strongly activates on second‐person “you” and surrounding words in instructional or advisory contexts.

    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
     ہمارا
    0.88
    हमने
    0.78
     আমাদের
    0.75
    <unused27>
    0.74
     ہماری
    0.74
    新たな
    0.73
    របស់យើង
    0.73
     нашу
    0.72
     僕
    0.71
     हमने
    0.71
    POSITIVE LOGITS
     tourist
    1.13
     traveler
    1.09
     viajeros
    1.01
     पर्यटक
    0.99
     tourists
    0.98
     travelers
    0.98
     turist
    0.97
     turista
    0.95
     touristic
    0.94
     locals
    0.94
    Activations Density 0.463%

    No Known Activations