© 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. 73751
    Prev
    Next
    INDEX
    Explanations

    plotting marker shapes and sizes

    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
    remes
    -0.85
    boné
    -0.82
    ragan
    -0.77
    राब
    -0.75
    резать
    -0.75
    ╚
    -0.75
     общего
    -0.72
    égek
    -0.72
    igsaw
    -0.72
    реза
    -0.71
    POSITIVE LOGITS
     dots
    1.75
     size
    1.70
     dot
    1.53
    PointSize
    1.47
    size
    1.39
     circle
    1.35
     Dots
    1.34
    Dots
    1.33
     scatter
    1.32
     sizes
    1.30
    Activations Density 0.042%

    No Known Activations