© 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. 10-GEMMASCOPE-RES-131K
    7. 119431
    Prev
    Next
    INDEX
    Explanations

    code and configuration structures

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

    deeply nested structured data, particularly JSON objects with multiple levels of indentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron primarily detects standalone numeric literals (numbers) in the text.

    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
    Кара
    -1.47
     atau
    -1.42
    ヵ
    -1.34
    Пет
    -1.31
    Läh
    -1.29
    Lain
    -1.28
    8
    -1.27
    лят
    -1.25
    replyreport
    -1.23
     intéressant
    -1.23
    POSITIVE LOGITS
     restes
    1.54
     rijden
    1.48
     Erkrank
    1.43
     cambiando
    1.36
    fficking
    1.36
    GETHER
    1.34
     deserto
    1.31
     zwi
    1.31
     ᾿
    1.30
    ః
    1.30
    Activations Density 0.037%

    No Known Activations