© 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. 22-GEMMASCOPE-RES-131K
    7. 54327
    Prev
    Next
    INDEX
    Explanations

    intensifiers and emphatic descriptions

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

    This neuron fires on positive evaluative adjectives and adverbs (e.g. comfortable, fabulous, simple, quick) used to praise or recommend something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -2.17
     two
    -2.09
     because
    -2.09
     during
    -2.06
     three
    -1.95
     for
    -1.94
     their
    -1.90
     at
    -1.89
     those
    -1.88
     while
    -1.88
    POSITIVE LOGITS
     delightfully
    1.72
     ſever
    1.69
     wonderfully
    1.67
     decidedly
    1.65
     unbelievably
    1.62
     ridiculously
    1.61
     goofy
    1.60
     captivating
    1.59
     ludicrous
    1.58
     magnificent
    1.56
    Activations Density 0.034%

    No Known Activations