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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102740
    Prev
    Next
    INDEX
    Explanations

    javascript event handlers and declarations

    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
    emptions
    -0.92
     setTotal
    -0.85
     setDate
    -0.84
    ất
    -0.82
     isInitialized
    -0.81
     setUsername
    -0.81
     bescha
    -0.80
     terang
    -0.79
     encontraron
    -0.78
    сім
    -0.78
    POSITIVE LOGITS
     handle
    3.73
    handle
    3.00
     Handle
    2.61
     handles
    2.59
    Handle
    2.53
     handled
    2.31
     handling
    2.20
     Handles
    2.09
    HANDLE
    1.98
     HANDLE
    1.96
    Activations Density 0.006%

    No Known Activations