© 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. 104062
    Prev
    Next
    INDEX
    Explanations

    programming calls

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

    function parameter lists in programming code, especially closing parentheses after type declarations.

    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
     but
    -1.23
    '){
    -1.20
    |'\
    -1.20
    = 
    -1.20
    ⏑
    -1.19
    hetamine
    -1.15
     storyline
    -1.14
     ultimi
    -1.14
    dok
    -1.11
     مليون
    -1.11
    POSITIVE LOGITS
     istället
    1.28
     ALSO
    1.22
    ühnen
    1.21
    Selama
    1.21
     graag
    1.20
     länge
    1.17
    負責
    1.16
    >
    1.16
     jöv
    1.15
     ángel
    1.14
    Activations Density 0.102%

    No Known Activations