© 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. 101490
    Prev
    Next
    INDEX
    Explanations

    object property access or assignment

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

    property access on objects or variables in code, particularly using the dot notation.

    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
     of
    -1.97
    袛
    -1.85
    ︱
    -1.68
    踭
    -1.57
     hecta
    -1.57
    甞
    -1.54
    壜
    -1.52
    扨
    -1.52
    僰
    -1.52
    鼉
    -1.49
    POSITIVE LOGITS
     are
    1.67
     could
    1.59
    There
    1.53
    一件
    1.51
     or
    1.48
     plethora
    1.47
    这些
    1.46
     oftentimes
    1.45
     geringen
    1.45
     may
    1.42
    Activations Density 0.075%

    No Known Activations