© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7034
    Prev
    Next
    INDEX
    Explanations

    degrees in fields of study

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

    The neuron fires strongly on the preposition “in” when it introduces academic details—fields of study, degrees, or institutional affiliations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Klem
    -1.62
    栝
    -1.60
    閦
    -1.52
    上学
    -1.52
    ちゃんの
    -1.52
     sternly
    -1.49
    慊
    -1.49
     connus
    -1.49
     jaula
    -1.46
    隄
    -1.46
    POSITIVE LOGITS
     sebagai
    1.49
    ÑO
    1.49
     اهل
    1.39
    what
    1.39
     uji
    1.36
    from
    1.34
    bbons
    1.34
     Stär
    1.33
    рию
    1.33
     bernama
    1.32
    Activations Density 0.016%

    No Known Activations