© 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. 2843
    Prev
    Next
    INDEX
    Explanations

    journey and travel

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

    The main thing this neuron does is detect references to travel plans or trip‐related terms.

    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
    সম্মত
    0.59
    ات
    0.57
     الموجود
    0.57
     सीधा
    0.54
    avasti
    0.54
     Shun
    0.53
     diện
    0.53
    ՞
    0.52
    ranu
    0.52
    ାର
    0.52
    POSITIVE LOGITS
     Into
    0.89
     trips
    0.88
     into
    0.88
     trip
    0.86
     itineraries
    0.85
     undertaken
    0.81
     туда
    0.80
     Across
    0.78
     Trips
    0.78
     afield
    0.77
    Activations Density 0.329%

    No Known Activations