© 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. 45384
    Prev
    Next
    INDEX
    Explanations

    Canadian research and academia

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

    The neuron detects formal academic affiliations and institutional or organizational titles in scholarly text.

    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
    icale
    -0.77
     вещь
    -0.75
     インテリア
    -0.75
     conseille
    -0.73
    tecs
    -0.72
     Guild
    -0.72
     Textbook
    -0.70
     Convenient
    -0.70
     Wils
    -0.70
    ductor
    -0.70
    POSITIVE LOGITS
     Canada
    1.20
    Canada
    1.11
    Canadian
    1.05
     Canadian
    1.05
     Canadians
    0.93
     jsonObj
    0.80
     HQ
    0.79
    Ottawa
    0.78
     canadi
    0.78
     Ottawa
    0.78
    Activations Density 0.030%

    No Known Activations