© 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. 59473
    Prev
    Next
    INDEX
    Explanations

    ministry of education

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

    The neuron detects mentions of government ministries by firing on the tokens in “Ministry of …​” institutional names.

    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
    ?
    -1.79
    .”
    -1.73
     in
    -1.55
    ()]);
    -1.52
     Они
    -1.51
    ">
    -1.49
    "><!--
    -1.45
    ();
    -1.43
     Нов
    -1.41
    );
    -1.34
    POSITIVE LOGITS
     própri
    2.08
     schermata
    1.80
     AQUI
    1.80
     ministra
    1.80
     anún
    1.77
     autocollant
    1.73
     indiví
    1.72
    鶫
    1.72
     márm
    1.70
    姈
    1.68
    Activations Density 0.021%

    No Known Activations