© 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. 25749
    Prev
    Next
    INDEX
    Explanations

    `Murr` minister

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

    This neuron fires most strongly on very common English function words (articles, prepositions, conjunctions).

    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
     couscous
    -0.75
     Cinderella
    -0.75
     verursacht
    -0.74
     veter
    -0.72
     Notwithstanding
    -0.71
     kacang
    -0.69
     vậy
    -0.69
    ShortName
    -0.68
    ◞
    -0.68
    网页
    -0.68
    POSITIVE LOGITS
    冒険
    0.85
    ïse
    0.84
    wezi
    0.79
     interes
    0.79
    dhism
    0.79
     рабочий
    0.77
     záz
    0.76
     الجيش
    0.76
    сного
    0.75
     dred
    0.75
    Activations Density 0.016%

    No Known Activations