© 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. 92564
    Prev
    Next
    INDEX
    Explanations

    code and content starters

    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
     had
    -0.95
     people
    -0.85
     has
    -0.84
     then
    -0.82
     hayas
    -0.81
     in
    -0.79
     during
    -0.78
    Church
    -0.75
     manages
    -0.74
     pengh
    -0.74
    POSITIVE LOGITS
    CAPÍTULO
    1.01
    ljiv
    0.95
    |}{
    0.94
    smiley
    0.93
    Напомним
    0.93
    faccia
    0.91
    ませんでした
    0.91
    oftware
    0.90
    toyage
    0.90
     smiley
    0.90
    Activations Density 0.000%

    No Known Activations