© 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. 34-GEMMASCOPE-RES-131K
    7. 49169
    Prev
    Next
    INDEX
    Explanations

    java code keywords

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

    The neuron fires on code tokens that invoke stream‐style collection operations (e.g. “stream,” “collect,” “Collectors,” “groupingBy,” “map,” etc.).

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

    No Comments

    Negative Logits
     eikä
    -0.81
    ใน
    -0.77
     Aussehen
    -0.77
    乡村
    -0.77
    herbe
    -0.75
    utada
    -0.75
    argent
    -0.75
    рь
    -0.73
     teniendo
    -0.73
     abordar
    -0.73
    POSITIVE LOGITS
     MwSt
    0.96
     INTO
    0.88
    Koi
    0.84
    Forgot
    0.84
    Ivy
    0.82
    ṗ
    0.82
     INITIAL
    0.82
     Fury
    0.82
     BUTTER
    0.81
     CCL
    0.80
    Activations Density 0.003%

    No Known Activations