© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129424
    Prev
    Next
    INDEX
    Explanations

    minister role or action

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

    This neuron detects mentions of government ministerial titles (e.g. “Minister,” “Ministry,” “Ministerial”).

    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
     процессов
    -2.94
     haupts
    -2.59
     surpass
    -2.50
     whatnot
    -2.48
     інших
    -2.44
    到着
    -2.34
     Guaranteed
    -2.33
     peně
    -2.30
     svých
    -2.30
     lessen
    -2.30
    POSITIVE LOGITS
    .
    3.31
    at
    2.64
     to
    2.50
    鹟
    2.48
     =
    2.41
    酲
    2.33
    ),
    2.28
    ۹
    2.25
    鹪
    2.25
    祼
    2.22
    Activations Density 0.009%

    No Known Activations