© 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. 22-GEMMASCOPE-RES-131K
    7. 27584
    Prev
    Next
    INDEX
    Explanations

    generics and type parameters

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

    The main thing this neuron does is detect generic type parameter syntax (e.g. type names in angle-bracket declarations and bounds).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    opie
    -1.02
    了很多
    -1.02
     akumulator
    -0.99
     mobilier
    -0.98
     belki
    -0.96
    ほうが
    -0.96
     Mentre
    -0.96
     Estaba
    -0.96
    ייה
    -0.96
    了许多
    -0.94
    POSITIVE LOGITS
    Then
    1.30
    Тогда
    1.09
     then
    1.00
    <>();
    0.99
    Both
    0.97
    思议
    0.96
     both
    0.93
    Each
    0.91
    atürk
    0.91
    グ
    0.91
    Activations Density 0.005%

    No Known Activations