© 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. 34-GEMMASCOPE-RES-131K
    7. 98442
    Prev
    Next
    INDEX
    Explanations

    Prime Minister and advisors

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

    The main thing this neuron does is detect numeric tokens (especially year numbers and other multi-digit figures).

    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
    ederen
    -0.86
     Zeus
    -0.81
    👑
    -0.81
    原标题
    -0.81
    ドライ
    -0.78
    コットン
    -0.75
    ණ
    -0.75
    妯
    -0.74
     Lecturer
    -0.74
     dégustation
    -0.73
    POSITIVE LOGITS
     ministers
    1.70
     minister
    1.66
     Minister
    1.54
     Prime
    1.50
     advisor
    1.45
     prime
    1.41
     adviser
    1.37
    Minister
    1.34
    Prime
    1.31
     advisors
    1.28
    Activations Density 0.045%

    No Known Activations