© 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. 1899
    Prev
    Next
    INDEX
    Explanations

    highly descriptive adjectives

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

    The neuron primarily activates on occurrences of the adverb “highly.”

    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
    -2.41
     to
    -2.38
     a
    -2.13
     about
    -1.93
     than
    -1.81
     my
    -1.77
     its
    -1.72
     Likewise
    -1.71
     anderen
    -1.70
     are
    -1.67
    POSITIVE LOGITS
     bym
    1.79
     adhesivo
    1.76
     giapp
    1.70
    ز
    1.59
     mój
    1.59
     decoracion
    1.55
     廣
    1.53
     стоковые
    1.52
    الش
    1.50
     высокая
    1.48
    Activations Density 0.009%

    No Known Activations