© 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. 127907
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on multi-syllable, domain-specific technical nouns and terminology.

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

    change or transition description

    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
    Nu
    -1.13
    Õ
    -0.95
    Lu
    -0.93
    ایک
    -0.92
    jt
    -0.92
    ntilde
    -0.92
     premières
    -0.90
    ग
    -0.90
     sog
    -0.90
     reinigen
    -0.89
    POSITIVE LOGITS
     during
    1.39
     from
    1.36
     will
    1.34
     before
    1.28
     at
    1.23
     until
    1.19
    ⦑
    1.14
     through
    1.13
     just
    1.13
     within
    1.13
    Activations Density 0.140%

    No Known Activations