© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54263
    Prev
    Next
    INDEX
    Explanations

    Minister of

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

    The neuron specifically detects occurrences of the word “Minister” used as a government office title.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     процессов
    -2.61
     haupts
    -2.44
     lessen
    -2.39
    .”
    -2.27
     větší
    -2.19
    寕
    -2.19
     surpass
    -2.17
     beliebtesten
    -2.16
     profundos
    -2.16
     zweif
    -2.16
    POSITIVE LOGITS
    鹟
    2.66
    .
    2.63
    酲
    2.45
    𖥧
    2.33
     diskusi
    2.33
    at
    2.33
    鹪
    2.30
    ࿊
    2.22
     This
    2.17
    Как
    2.11
    Activations Density 0.010%

    No Known Activations