© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100264
    Prev
    Next
    INDEX
    Explanations

    java class names

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

    class names or type names in programming code, particularly when they appear after keywords like "import", "extends", or in 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
     and
    -2.28
     purely
    -1.55
     only
    -1.38
    鶯
    -1.36
     bicicletas
    -1.35
    Why
    -1.34
     will
    -1.29
    While
    -1.28
    !(
    -1.24
     wyłącznie
    -1.24
    POSITIVE LOGITS
     that
    1.37
     you
    1.31
    ometries
    1.29
     файлы
    1.26
    owali
    1.25
     in
    1.24
    一点点
    1.23
    很高
    1.23
     présentes
    1.22
     his
    1.21
    Activations Density 0.033%

    No Known Activations