© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98925
    Prev
    Next
    INDEX
    Explanations

    aid and supplies

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

    This neuron fires on terms describing the logistics and quantities of humanitarian relief deliveries—shipping, urgent aid, numbers of trucks and supplies.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    тату
    -0.91
     cerveau
    -0.88
    horst
    -0.84
     поч
    -0.81
     Perché
    -0.81
     Extensions
    -0.81
    🌼
    -0.80
    TSA
    -0.80
    भा
    -0.79
     ashtray
    -0.79
    POSITIVE LOGITS
     medicines
    1.29
     equipment
    1.28
     materials
    1.26
     medicine
    1.23
     medication
    1.16
     blankets
    1.15
     medications
    1.15
     seeds
    1.08
     starter
    1.06
     medical
    1.04
    Activations Density 0.018%

    No Known Activations