© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110869
    Prev
    Next
    INDEX
    Explanations

    School of

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

    The neuron selectively activates on names of institutional or organizational units—especially academic schools, departments, centers, faculties, and similar headings.

    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
    ating
    -1.34
     their
    -1.33
    放下
    -1.26
     raccomand
    -1.23
     TAMBIÉN
    -1.22
    good
    -1.19
     weiteres
    -1.19
    粜
    -1.15
    century
    -1.14
    麃
    -1.14
    POSITIVE LOGITS
     and
    1.77
     as
    1.63
     should
    1.41
     of
    1.37
    Жит
    1.23
     in
    1.20
     through
    1.19
     by
    1.18
    üedad
    1.16
     jigsaw
    1.15
    Activations Density 0.056%

    No Known Activations