© 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. 55982
    Prev
    Next
    INDEX
    Explanations

    Stud Boy, Trumai, Q:

    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
     百
    -0.84
    まえ
    -0.77
     minutes
    -0.76
    EdgeInsets
    -0.76
    HERE
    -0.75
    Minute
    -0.74
    edin
    -0.73
     minute
    -0.73
    Character
    -0.70
     moje
    -0.70
    POSITIVE LOGITS
    няет
    0.79
    Wpf
    0.72
    Vastaa
    0.72
    招待
    0.70
    塹
    0.69
     erbjuder
    0.68
    almente
    0.68
    rétaire
    0.68
     carinho
    0.68
     Lance
    0.68
    Activations Density 0.013%

    No Known Activations