© 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. 38615
    Prev
    Next
    INDEX
    Explanations

    catholic colleges and universities

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

    This neuron responds to multi‐token proper names of academic institutions (e.g., university or college names and related domains).

    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
    ﮨ
    -1.68
    ꦧ
    -1.42
     Some
    -1.39
     játék
    -1.38
    g
    -1.36
    v
    -1.36
     first
    -1.35
     with
    -1.32
    也
    -1.32
     are
    -1.30
    POSITIVE LOGITS
    ments
    1.59
    Välisling
    1.41
    Catholic
    1.41
     Catholic
    1.35
    brtc
    1.32
    )\}$
    1.29
    )}{
    1.27
    лись
    1.25
     ?>">
    1.25
    delmi
    1.24
    Activations Density 0.144%

    No Known Activations