© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72507
    Prev
    Next
    INDEX
    Explanations

    humanitarian assistance and situation

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

    The neuron specializes in detecting descriptions of large‐scale humanitarian crises and their urgency—marking words that signal humanitarian assistance, affected populations, displacement, and crisis magnitude.

    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
     religieuses
    -1.88
     chré
    -1.72
     religieux
    -1.67
     eſt
    -1.56
     that
    -1.52
     ſi
    -1.48
     valla
    -1.45
     solamente
    -1.44
     Eſ
    -1.41
    ɜ
    -1.41
    POSITIVE LOGITS
    ּוֹ
    2.14
    ְּ
    2.13
    ֶּ
    2.08
    ִּ
    1.88
    ᾽
    1.72
    ַּ
    1.71
    ﻷ
    1.63
    ְר
    1.62
     бампер
    1.62
    ֵּ
    1.61
    Activations Density 0.025%

    No Known Activations