© 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. 19475
    Prev
    Next
    INDEX
    Explanations

    adjectives separated by commas

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

    The neuron fires on strongly positive descriptive adjectives and adverbs (praise words) that characterize something as appealing or high-quality.

    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
     of
    -3.39
     other
    -2.22
     in
    -2.16
     from
    -2.16
     for
    -2.06
     to
    -1.73
     verschied
    -1.66
    ”,
    -1.64
     or
    -1.53
     größeren
    -1.53
    POSITIVE LOGITS
     and
    2.39
     condicionado
    1.77
     erreur
    1.56
     doit
    1.54
    
    1.53
    .«
    1.51
     دیجیتال
    1.48
    {
    1.48
    joyed
    1.48
     couleur
    1.48
    Activations Density 0.065%

    No Known Activations