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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93046
    Prev
    Next
    INDEX
    Explanations

    code data types and declarations

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

    The neuron activates on tokens that represent data types, type names, or schema/type‐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_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
    KeySpec
    -0.94
    Veterans
    -0.92
     donc
    -0.89
    ଃ
    -0.89
    uded
    -0.89
     with
    -0.88
    jay
    -0.85
    usions
    -0.84
     für
    -0.84
     for
    -0.84
    POSITIVE LOGITS
    镐
    1.01
    Selon
    0.94
    してきました
    0.91
     Sepul
    0.89
    ipolar
    0.89
    animo
    0.89
     prendra
    0.89
     بعدی
    0.87
     posteriormente
    0.87
     попробовать
    0.86
    Activations Density 0.005%

    No Known Activations