© 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. 70227
    Prev
    Next
    INDEX
    Explanations

    generic type parameters

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

    The neuron activates on occurrences of generic type parameters and related generic‐syntax tokens (like T, S, angle brackets, commas) 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
     acepción
    -1.77
    〼
    -1.75
    Carrot
    -1.71
    酩
    -1.71
     meditación
    -1.69
     sabiduría
    -1.69
    泺
    -1.68
    曏
    -1.67
    外人
    -1.66
     oído
    -1.65
    POSITIVE LOGITS
    \
    2.27
    2
    2.22
    4
    2.17
    3
    2.17
    at
    2.05
    8
    2.05
    9
    2.03
    0
    1.95
    ;
    1.94
    “
    1.80
    Activations Density 0.012%

    No Known Activations