© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112296
    Prev
    Next
    INDEX
    Explanations

    software development tools

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

    references to software tools, applications, and development environments, particularly IDEs, text editors, and programming platforms.

    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
     about
    -1.74
    景观
    -1.48
    냑
    -1.40
     メニュー
    -1.38
    ventura
    -1.30
     incluso
    -1.28
    蕴
    -1.27
    @[+][
    -1.26
    "",
    -1.25
     his
    -1.24
    POSITIVE LOGITS
     réus
    1.38
     medición
    1.36
     saisi
    1.33
    duga
    1.29
     fallu
    1.28
    ultura
    1.27
     such
    1.27
    🥿
    1.24
     Selamat
    1.23
     merken
    1.23
    Activations Density 0.217%

    No Known Activations