© 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. 22-GEMMASCOPE-RES-131K
    7. 13855
    Prev
    Next
    INDEX
    Explanations

    Educational institutions and medical departments

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

    The neuron is sensitive to tokens that appear in the names of educational institutions (e.g. “Engineering,” “College,” “University,” “Institute”).

    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
    üman
    -1.10
     ghz
    -1.04
     perusahaan
    -1.02
     chicco
    -1.01
     seçenek
    -0.98
     cabrio
    -0.96
     ianuarie
    -0.96
    amethasone
    -0.96
    😤
    -0.94
    -~
    -0.94
    POSITIVE LOGITS
     acredit
    1.20
     Stornier
    1.13
    鋱
    1.12
    ได้รับ
    1.11
    cephala
    1.09
     schmerz
    1.08
     gefe
    1.07
     students
    1.06
    IATION
    1.05
    IVENESS
    1.04
    Activations Density 0.028%

    No Known Activations