© 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. 93433
    Prev
    Next
    INDEX
    Explanations

    university names and degrees

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

    The neuron is detecting mentions of academic degrees and affiliated educational institutions (e.g., university names and degree titles).

    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
     to
    -1.21
    に行きました
    -1.08
     questions
    -1.05
    -0.99
     plot
    -0.98
    に行ってきました
    -0.98
     ciasc
    -0.94
    なのが
    -0.94
     pronti
    -0.94
    [
    -0.94
    POSITIVE LOGITS
     många
    1.26
    nhung
    1.19
     siè
    1.18
     réjou
    1.18
     fidé
    1.16
     triomphe
    1.16
    Kf
    1.15
    참고
    1.13
     déli
    1.13
     keď
    1.10
    Activations Density 0.033%

    No Known Activations