© 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. 25050
    Prev
    Next
    INDEX
    Explanations

    after words

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

    The neuron strongly activates on mid-to-long content words (tokens of roughly four or more letters) rather than short function words.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     and
    -0.98
    ™
    -0.85
     اللح
    -0.85
    อี
    -0.81
     herein
    -0.78
     народов
    -0.77
     breeder
    -0.77
     dels
    -0.76
     nessa
    -0.76
     insuff
    -0.75
    POSITIVE LOGITS
     afterwards
    1.48
     بعد
    1.29
     after
    1.27
     afterward
    1.24
    之後
    1.23
     násled
    1.22
     depois
    1.18
     después
    1.17
     после
    1.13
    之后
    1.09
    Activations Density 0.132%

    No Known Activations