© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44632
    Prev
    Next
    INDEX
    Explanations

    University, Act, Senate

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

    The neuron activates on mentions of educational institutions or academic units (e.g. colleges, universities, institutes, departments).

    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
     zyn
    -1.31
    榦
    -1.29
     dispen
    -1.27
     zoll
    -1.25
     javafx
    -1.20
     canad
    -1.19
    peka
    -1.19
     kanak
    -1.18
     iſt
    -1.13
     gres
    -1.13
    POSITIVE LOGITS
    <bos>
    1.33
     Persönlichkeit
    1.17
     Entscheid
    1.15
     Beziehung
    1.14
     wichtigen
    1.11
     enemigo
    1.09
     Gegens
    1.07
     Furcht
    1.06
     Überras
    1.06
     Kampagne
    1.05
    Activations Density 0.042%

    No Known Activations