© 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. 10-GEMMASCOPE-RES-131K
    7. 41583
    Prev
    Next
    INDEX
    Explanations

    pronounopinionrelationship

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

    The neuron fires most strongly on extremely common, high‐frequency words (e.g. “to,” “about,” “their,” “opinion,” etc.).

    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
     to
    -1.82
     in
    -1.74
     also
    -1.73
    佉
    -1.72
     first
    -1.72
    istice
    -1.65
    تفصیلات
    -1.63
     Also
    -1.63
     more
    -1.63
    Every
    -1.62
    POSITIVE LOGITS
     it
    2.97
     them
    2.83
     dekoratif
    1.87
     haast
    1.80
     him
    1.79
     you
    1.70
     tropicales
    1.63
     diki
    1.63
    犹如
    1.62
     maksi
    1.59
    Activations Density 0.124%

    No Known Activations