© 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. 59806
    Prev
    Next
    INDEX
    Explanations

    agriculture minister titles

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

    The neuron strongly activates on proper names and formal titles (e.g. government officeholders and organizational roles).

    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
     pizza
    -0.75
    engi
    -0.71
     Human
    -0.70
     afge
    -0.69
     Schools
    -0.69
     potter
    -0.68
    findAll
    -0.68
     school
    -0.67
     circuit
    -0.67
    MessageDigest
    -0.67
    POSITIVE LOGITS
     FAO
    1.54
    FAO
    1.35
     Agriculture
    1.22
    Agriculture
    1.20
     agriculture
    1.17
     USDA
    1.15
    USDA
    1.13
    Food
    1.02
     Food
    0.99
     agricultural
    0.96
    Activations Density 0.026%

    No Known Activations