© 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. 110539
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

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

    code snippets or blocks, particularly whitespace and formatting characters that structure programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h2>
    -1.77
    Она
    -1.66
    kurtka
    -1.63
    inguez
    -1.62
     搞笑
    -1.59
     简约
    -1.56
    鹟
    -1.55
     إذا
    -1.53
    fertig
    -1.52
     pantaloni
    -1.52
    POSITIVE LOGITS
    .
    1.59
    的吧
    1.49
     they
    1.40
    :
    1.40
    #
    1.38
    是很
    1.38
     
    1.30
    的了
    1.30
     its
    1.28
    OGRAPH
    1.28
    Activations Density 0.012%

    No Known Activations