© 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. 90442
    Prev
    Next
    INDEX
    Explanations

    education and institutions

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

    The neuron is strongly activated by words naming or describing educational institutions and their administrative bodies (e.g. school, education, board, university).

    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
    瘠
    -0.79
     mahasiswa
    -0.75
    mesan
    -0.73
     beta
    -0.69
     üzerinde
    -0.68
    盆
    -0.66
    ‵
    -0.66
     Meth
    -0.66
    beta
    -0.66
    gdx
    -0.65
    POSITIVE LOGITS
     RTE
    1.03
    RTE
    0.98
    Girl
    0.93
     DIET
    0.93
     DISE
    0.87
    KAZ
    0.85
     Corolla
    0.81
     girls
    0.79
     Accreditation
    0.79
    NCF
    0.78
    Activations Density 0.002%

    No Known Activations