© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10916
    Prev
    Next
    INDEX
    Explanations

    code class definitions

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

    class or constructor names in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects CamelCase type and class names (and related identifiers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -1.58
     at
    -1.48
     of
    -1.33
     to
    -1.31
     and
    -1.28
    >|</
    -1.27
     verspre
    -1.18
     uchun
    -1.16
    🌟
    -1.11
     into
    -1.10
    POSITIVE LOGITS
     who
    1.56
     know
    1.47
     previously
    1.46
     already
    1.44
     other
    1.43
     alfombra
    1.42
     such
    1.41
     restauración
    1.39
     escase
    1.37
     ganzes
    1.36
    Activations Density 0.059%

    No Known Activations