© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127644
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on emphatic evaluative adjectives and intensifiers (e.g. “real,” “true,” “absolute,” “utter,” “pure”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    intensifiers followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    aneity
    -1.90
     唯美
    -1.88
    が
    -1.80
    というわけで
    -1.79
     插图
    -1.78
     incrí
    -1.76
    栞
    -1.75
     مناط
    -1.73
    それにしても
    -1.65
    が多く
    -1.64
    POSITIVE LOGITS
    ようです
    1.85
    L
    1.77
    金币
    1.70
    つづく
    1.62
    為に
    1.62
     otthon
    1.61
    J
    1.59
    r
    1.52
    A
    1.52
    ところに
    1.51
    Activations Density 0.029%

    No Known Activations