© 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. 11885
    Prev
    Next
    INDEX
    Explanations

    disseminate research and resources

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

    The neuron fires on the titles and proper names of organizations, conferences, publications, 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
     PMI
    -0.87
     OMR
    -0.80
     setTotal
    -0.73
    Elles
    -0.72
    био
    -0.70
    zsche
    -0.70
    IsActive
    -0.69
     Thereafter
    -0.69
     kæ
    -0.67
     चित्र
    -0.66
    POSITIVE LOGITS
     Clearing
    1.38
     clearing
    1.37
     disseminate
    1.09
     Disse
    1.07
     dissemination
    1.05
     disseminating
    1.00
    clearing
    0.98
    ERIC
    0.97
     resource
    0.89
    Clearing
    0.88
    Activations Density 0.035%

    No Known Activations