© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7779
    Prev
    Next
    INDEX
    Explanations

    travel plans and activities

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

    This neuron fires on text describing travel itineraries or lists of tourist/venue activities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    descriptive language about travel experiences and activities, particularly phrases that invite exploration or engagement with destinations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of travel and tourism experiences—sightseeing, tours, itineraries, and visiting attractions—often written in second-person, promotional tone.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     ремон
    0.84
    довле
    0.82
     deformed
    0.79
     Schottky
    0.78
     ஆண
    0.72
     กรรม
    0.71
     defamation
    0.68
     adına
    0.68
     austenitic
    0.68
     impost
    0.66
    POSITIVE LOGITS
     sightseeing
    1.84
     экскур
    1.59
     excursions
    1.47
    Exploring
    1.45
    行程
    1.41
     itinerary
    1.39
     wisata
    1.39
     Exploring
    1.38
     excursion
    1.38
     tour
    1.37
    Activations Density 0.855%

    No Known Activations