© 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. 101763
    Prev
    Next
    INDEX
    Explanations

    code and language elements

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

    the word "unused" in programming code comments and directives (particularly in linting rules and compiler warnings).

    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
     enää
    -1.29
    ！』
    -1.21
     lukisan
    -1.18
     sekitar
    -1.14
    
    -1.13
     فرز
    -1.13
     tiden
    -1.12
    薬品
    -1.12
    杁
    -1.11
    ゛
    -1.09
    POSITIVE LOGITS
    мання
    1.21
     .
    1.16
     eleições
    1.12
     Sünde
    1.12
     Gemüse
    1.12
    Customs
    1.09
     配件
    1.08
     comparação
    1.07
     posibil
    1.07
    urias
    1.07
    Activations Density 0.007%

    No Known Activations