© 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. 32822
    Prev
    Next
    INDEX
    Explanations

    class or property names

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

    This neuron fires on uppercase identifier tokens (especially those in ALL_CAPS or snake‐case) such as configuration or constant names.

    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
    
    -1.53
     conster
    -1.48
    </h2>
    -1.47
    ኧ
    -1.47
    そして
    -1.43
     endast
    -1.42
    изнь
    -1.38
    The
    -1.38
     solida
    -1.37
    Custom
    -1.36
    POSITIVE LOGITS
     or
    1.95
     that
    1.88
     at
    1.73
     which
    1.63
     and
    1.62
     in
    1.61
     for
    1.58
     as
    1.50
     from
    1.49
     to
    1.47
    Activations Density 0.036%

    No Known Activations