© 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. 103096
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and coordinates

    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
     amalgam
    -0.87
     globales
    -0.81
     эпо
    -0.81
    mover
    -0.80
    itself
    -0.77
    timing
    -0.77
    hibitor
    -0.77
     timing
    -0.76
    feel
    -0.76
    XRD
    -0.75
    POSITIVE LOGITS
     finish
    0.98
     second
    0.88
     difference
    0.86
     Що
    0.84
     final
    0.82
     事業
    0.79
     point
    0.79
     św
    0.79
     abandonar
    0.78
     start
    0.75
    Activations Density 0.012%

    No Known Activations