© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57703
    Prev
    Next
    INDEX
    Explanations

    object pointers and handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Localized
    -0.86
     Learned
    -0.81
    逐
    -0.78
     Historical
    -0.75
     Named
    -0.74
    嶋
    -0.72
     gemeente
    -0.72
    商品説明
    -0.69
     Discovered
    -0.68
    太子
    -0.68
    POSITIVE LOGITS
     handle
    1.18
    handle
    1.08
    Handle
    1.05
     HANDLE
    1.02
    对象
    1.02
     pointer
    1.00
     object
    1.00
    ptr
    0.98
     IntPtr
    0.97
     handles
    0.95
    Activations Density 0.037%

    No Known Activations