© 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. 16574
    Prev
    Next
    INDEX
    Explanations

    class or struct names ending in Args

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

    This neuron activates on fragments of programming identifiers—especially CamelCase or PascalCase class, method, or type names 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
    toner
    -1.22
    anmar
    -1.15
     our
    -1.09
    playa
    -1.09
    crap
    -1.08
     ANNOUNC
    -1.07
    penguin
    -1.03
    мання
    -1.02
    へ向
    -0.98
    hobo
    -0.98
    POSITIVE LOGITS
    how
    1.29
    скольку
    1.22
    may
    1.21
    being
    1.21
    اگر
    1.18
    any
    1.17
     DialogInterface
    1.16
    have
    1.16
    iteness
    1.15
    should
    1.14
    Activations Density 0.013%

    No Known Activations