© 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. 45200
    Prev
    Next
    INDEX
    Explanations

    Ministry of X

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

    The neuron fires on occurrences of the phrase “Ministry of” (i.e. government ministry 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
    montre
    -2.03
    🆆
    -1.91
    extAlignment
    -1.81
    䊏
    -1.80
    ه‌ای
    -1.78
    ">(</
    -1.77
    思议
    -1.77
    libft
    -1.77
    requipa
    -1.74
    Gilla
    -1.73
    POSITIVE LOGITS
    姈
    2.22
    你和
    2.03
    ”،
    1.93
    婓
    1.92
    ＆
    1.91
     mismos
    1.83
     bús
    1.82
    釓
    1.80
     to
    1.77
    .
    1.76
    Activations Density 0.003%

    No Known Activations