© 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. 34-GEMMASCOPE-RES-131K
    7. 77754
    Prev
    Next
    INDEX
    Explanations

    schools and academic departments

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

    The neuron activates on mentions of academic “School of …” names (i.e. tokens in institutional or departmental titles containing “School”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     visst
    -0.83
     Raoul
    -0.82
    拼音
    -0.77
    もしれない
    -0.76
     будут
    -0.76
    我也不
    -0.76
    还要
    -0.74
    مل
    -0.73
     invoices
    -0.73
    چه
    -0.72
    POSITIVE LOGITS
     of
    1.36
    🏫
    0.90
     ј
    0.89
     kode
    0.89
    kode
    0.83
     lasted
    0.83
     devoirs
    0.83
     kv
    0.82
     tinggi
    0.82
     kota
    0.82
    Activations Density 0.020%

    No Known Activations