© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    code block structure

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

    opening parentheses in code, particularly after keywords like "function", "if", or type constructors.

    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
    していました
    -1.36
     květ
    -1.34
     тільки
    -1.33
    Then
    -1.33
    鸝
    -1.27
     потім
    -1.26
    喲
    -1.26
    したいと思います
    -1.22
     muhte
    -1.20
     wahrscheinlich
    -1.19
    POSITIVE LOGITS
     lorsqu
    1.59
     kesi
    1.52
    hhhhhhhh
    1.35
     vasto
    1.31
     kasar
    1.29
     disiplin
    1.28
     lü
    1.23
     lorsque
    1.23
     kado
    1.23
     misterio
    1.22
    Activations Density 0.027%

    No Known Activations