© 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. 98549
    Prev
    Next
    INDEX
    Explanations

    software commands and components

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

    The neuron fires on code identifier tokens—especially API, class, or module names 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
    делы
    -1.12
     usan
    -1.04
     for
    -1.00
    欷
    -1.00
     korban
    -0.97
    の地
    -0.96
     morir
    -0.96
     gunakan
    -0.96
     détaillée
    -0.94
    tranh
    -0.94
    POSITIVE LOGITS
    mathrm
    1.05
     общий
    1.00
    俳優
    0.96
    니까
    0.96
     "./
    0.95
    only
    0.94
    今回は
    0.94
    upiter
    0.93
     foll
    0.93
    ...:
    0.93
    Activations Density 0.002%

    No Known Activations