© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14367
    Prev
    Next
    INDEX
    Explanations

    items carried or used

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

    This neuron spots mentions of packing or carrying personal gear and supplies.

    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_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
    ގެ
    0.70
     continueRoutine
    0.68
    érir
    0.62
    ອດ
    0.62
    ım
    0.61
    しょう
    0.60
    ون
    0.59
    ؤ
    0.59
     éste
    0.59
    öner
    0.58
    POSITIVE LOGITS
     backpacks
    0.97
     backpack
    0.89
     Lug
    0.84
     Backpack
    0.82
     loaded
    0.82
     mochila
    0.82
     luggage
    0.79
     baggage
    0.79
     Hiking
    0.78
    backpack
    0.78
    Activations Density 0.029%

    No Known Activations