© 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. 11725
    Prev
    Next
    INDEX
    Explanations

    unit tests and code descriptions

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

    test function declarations in code (particularly `it`, `test`, `describe`, and similar testing keywords).

    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
    ,
    -1.58
     from
    -1.27
     These
    -1.26
    Кроме
    -1.24
     丼
    -1.20
     móg
    -1.18
     useStyles
    -1.16
     tirantes
    -1.16
    Tapi
    -1.14
    Spesifikasi
    -1.14
    POSITIVE LOGITS
     to
    1.65
     first
    1.60
                              
    1.40
    ﻷ
    1.40
                                  
    1.38
     приготов
    1.35
    リース
    1.33
    ﻻ
    1.32
    機の
    1.28
    begin
    1.26
    Activations Density 0.021%

    No Known Activations