© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90227
    Prev
    Next
    INDEX
    Explanations

    drawing on canvas elements

    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
     composta
    -0.99
     armazenamento
    -0.95
    compos
    -0.92
     contratación
    -0.90
    Buna
    -0.88
    Versch
    -0.88
    Atención
    -0.88
     sottile
    -0.86
     china
    -0.86
     metals
    -0.85
    POSITIVE LOGITS
     Canvas
    1.52
    canvas
    1.42
     canvas
    1.29
    Canvas
    1.21
     canvases
    1.08
     textured
    1.05
     canvass
    1.03
    alleries
    0.99
     姆
    0.94
    🍻
    0.92
    Activations Density 0.005%

    No Known Activations