© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6976
    Prev
    Next
    INDEX
    Explanations

    international development and aid

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

    The neuron is primarily detecting numeric expressions (years, counts) and all-caps acronyms or organization names.

    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
     بیان
    -0.85
     seguros
    -0.69
    GUI
    -0.68
     Magnetic
    -0.68
    WAVE
    -0.67
    hyth
    -0.66
     babak
    -0.66
     hakk
    -0.66
    INATION
    -0.66
    endo
    -0.65
    POSITIVE LOGITS
     aid
    1.92
    Aid
    1.59
     Aid
    1.58
     USAID
    1.48
     Development
    1.45
     development
    1.44
    aid
    1.41
    Development
    1.38
     Overseas
    1.30
     overseas
    1.30
    Activations Density 0.029%

    No Known Activations