© 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. 22-GEMMASCOPE-RES-131K
    7. 13822
    Prev
    Next
    INDEX
    Explanations

    travels and visits

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

    The neuron fires on travel‐or itinerary‐related terms—words that denote stops, tours, trips, voyages, and similar journey segments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     resources
    -1.05
     also
    -1.04
     that
    -0.98
    tiden
    -0.97
    Etimología
    -0.97
    ないけど
    -0.95
    りますが
    -0.95
     سینم
    -0.94
     an
    -0.93
     objects
    -0.93
    POSITIVE LOGITS
    postolic
    1.24
    poptosis
    1.18
     visits
    1.16
    retirement
    1.13
     имму
    1.05
     visit
    1.05
     tours
    1.04
     everywhere
    1.03
     across
    1.03
     to
    1.03
    Activations Density 0.019%

    No Known Activations