© 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. 104570
    Prev
    Next
    INDEX
    Explanations

    configuration files and code

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

    code syntax elements like assignment operators, dots, underscores, and parentheses in programming languages and configuration files.

    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
    颪
    -1.73
    Println
    -1.52
    也都
    -1.45
     ancak
    -1.41
     little
    -1.38
    uteria
    -1.34
    StandardCharsets
    -1.34
    ⻬
    -1.34
     פֿ
    -1.32
    들은
    -1.30
    POSITIVE LOGITS
    cartera
    1.54
    tarjeta
    1.41
     aanz
    1.38
     fährt
    1.34
     your
    1.34
     prachtig
    1.32
     illustratie
    1.29
    ;
    1.28
     without
    1.27
    endif
    1.25
    Activations Density 0.184%

    No Known Activations