© 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. 32602
    Prev
    Next
    INDEX
    Explanations

    code declarations or assignments

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

    The neuron fires on all-uppercase identifier tokens—e.g. constant names or enum labels in code.

    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
     those
    -1.13
     as
    -1.12
    Those
    -1.05
     at
    -1.02
     on
    -1.01
     within
    -1.01
     important
    -1.00
     by
    -1.00
     during
    -0.99
     terrible
    -0.96
    POSITIVE LOGITS
     Dinas
    1.28
     rengi
    0.99
     vijf
    0.98
     umgangssprach
    0.97
    thirty
    0.97
     harán
    0.97
     thwarted
    0.96
    indir
    0.94
     комиссии
    0.93
     possi
    0.92
    Activations Density 0.015%

    No Known Activations