© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101874
    Prev
    Next
    INDEX
    Explanations

    introducing definitions or starting points

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

    The neuron fires most strongly on prominent topic words or headings—key content words that label or introduce the main subject of a section.

    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
     réalisateur
    -1.53
     encuentran
    -1.52
     personer
    -1.48
    ătate
    -1.44
     verhind
    -1.38
     gewor
    -1.38
    рации
    -1.36
     gebo
    -1.36
     acontecimientos
    -1.34
     our
    -1.34
    POSITIVE LOGITS
     where
    1.66
    </i>
    1.54
     Maybe
    1.34
    Maybe
    1.33
     with
    1.33
    入れた
    1.32
     they
    1.30
     and
    1.27
     until
    1.26
    してた
    1.26
    Activations Density 0.075%

    No Known Activations