© 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. 84676
    Prev
    Next
    INDEX
    Explanations

    Star Wars lore and citations

    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
    vinyl
    -0.75
     laser
    -0.72
    važ
    -0.71
     neki
    -0.70
    ଶ
    -0.69
     sexy
    -0.69
     ordered
    -0.68
    hláš
    -0.68
     Value
    -0.67
     Space
    -0.67
    POSITIVE LOGITS
     Carro
    0.85
     Prez
    0.82
     merid
    0.79
    edits
    0.79
    ijos
    0.78
     ладо
    0.77
     boca
    0.76
    ۗ
    0.76
     Excelsior
    0.75
    douard
    0.75
    Activations Density 0.011%

    No Known Activations