© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81335
    Prev
    Next
    INDEX
    Explanations

    humanitarian crisis topics

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

    The neuron activates strongly on mentions of armed conflict or humanitarian crises (e.g. wars, suffering, aid needs, and related terms).

    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
     exhilarating
    -0.83
    ignment
    -0.82
    chowy
    -0.81
    avao
    -0.81
     figli
    -0.81
    ifikationen
    -0.80
    غب
    -0.80
     eröffnet
    -0.79
     undesirable
    -0.78
    slu
    -0.78
    POSITIVE LOGITS
     humanitarian
    1.84
     Humanitarian
    1.46
     hunger
    1.34
     starvation
    1.22
     aid
    1.15
     food
    1.13
     famine
    1.09
     malnutrition
    1.09
    hunger
    1.07
    餓
    1.05
    Activations Density 0.040%

    No Known Activations