© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7868
    Prev
    Next
    INDEX
    Explanations

    camping and camp activities

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

    This neuron strongly activates on descriptive travel-brochure language detailing tourist accommodations, activities, and hospitality logistics.

    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
     मेट्रो
    0.85
     Downtown
    0.84
     downtown
    0.82
     sidewalk
    0.82
     cityscape
    0.81
     Midtown
    0.80
    🏙
    0.79
     città
    0.77
     मेयर
    0.74
    City
    0.73
    POSITIVE LOGITS
     camp
    2.22
     campsite
    2.14
     camping
    2.08
     campsites
    2.05
    キャンプ
    1.98
     campers
    1.95
     campfire
    1.95
    🏕
    1.89
     Camping
    1.85
    Camping
    1.84
    Activations Density 0.550%

    No Known Activations