© 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. 34-GEMMASCOPE-RES-131K
    7. 30030
    Prev
    Next
    INDEX
    Explanations

    Dragonfly, Copper, animal, rose, jelly, Iron, Crown, Liquid, lion

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

    names of software projects, programming libraries, or open source projects in source code.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    This neuron detects names of software projects, libraries, or code modules (often appearing as capitalized identifiers in include paths or copyright headers).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     several
    -0.97
     Several
    -0.97
     During
    -0.96
     during
    -0.96
     забезпе
    -0.92
    bibit
    -0.91
    Museo
    -0.90
     spē
    -0.90
     Throughout
    -0.87
    perfume
    -0.86
    POSITIVE LOGITS
    OS
    1.09
    (()
    0.98
    CAR
    0.98
    indd
    0.98
    Office
    0.96
    GL
    0.96
     Biosciences
    0.94
    Suite
    0.93
    mine
    0.93
     delightfully
    0.93
    Activations Density 0.220%

    No Known Activations