© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15201
    Prev
    Next
    INDEX
    Explanations

    dates and periods

    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_22/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
    (;;)
    -0.98
     ২০১
    -0.93
    🤸
    -0.90
     Piaget
    -0.85
     Vodka
    -0.83
    んだり
    -0.82
     copyrights
    -0.82
     Revealed
    -0.80
    合計
    -0.80
     creeds
    -0.80
    POSITIVE LOGITS
     decades
    1.79
     damals
    1.59
     years
    1.34
     décadas
    1.29
     early
    1.26
     década
    1.20
     Depression
    1.20
    當時
    1.15
     jaren
    1.13
     historically
    1.13
    Activations Density 0.241%

    No Known Activations