© 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. 59246
    Prev
    Next
    INDEX
    Explanations

    RH Bill, Filipino children, conditions under

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

    The neuron fires most strongly on tokens that appear in official or legal references—proper names, titles, sections/articles, dates, and other formal entities.

    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
     featuring
    -0.82
     waż
    -0.77
    摔
    -0.76
    intersect
    -0.75
    Featuring
    -0.75
    ッ
    -0.73
     converting
    -0.73
    rickson
    -0.72
    PropertyName
    -0.71
    ENES
    -0.70
    POSITIVE LOGITS
     peasant
    0.80
    rights
    0.72
     nạ
    0.71
    landa
    0.71
     peasants
    0.70
     broadest
    0.70
     czerwony
    0.70
     Bip
    0.69
     ngo
    0.69
     clutches
    0.68
    Activations Density 0.007%

    No Known Activations