© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10836
    Prev
    Next
    INDEX
    Explanations

    programming data types

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

    the opening angle bracket in generic type declarations (e.g., `List<T>`, `Set<T>`, `ArrayAdapter<String>`).

    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
    værende
    -1.51
     jt
    -1.44
    /*!
    
    -1.38
     hemd
    -1.37
     jurí
    -1.35
     You
    -1.34
    )、
    -1.32
     eficientes
    -1.31
     gruppe
    -1.31
    法则
    -1.30
    POSITIVE LOGITS
    0
    2.14
    7
    1.77
     if
    1.73
    !"
    1.66
     from
    1.46
     those
    1.43
    アレル
    1.40
    樒
    1.39
     weiterhin
    1.38
    ]&
    1.38
    Activations Density 0.003%

    No Known Activations