© 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. 22-GEMMASCOPE-RES-131K
    7. 75328
    Prev
    Next
    INDEX
    Explanations

    after, then, meanwhile

    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
    Through
    -0.99
    Waktu
    -0.98
    acquisto
    -0.94
     देते
    -0.90
    简称
    -0.87
     other
    -0.85
     doméstica
    -0.84
     сначала
    -0.83
    Other
    -0.83
    所需的
    -0.81
    POSITIVE LOGITS
     meanwhile
    1.30
     btw
    1.20
     násled
    1.15
     кстати
    1.13
     afterward
    1.09
     afterwards
    1.02
     vẫn
    1.00
     thereafter
    0.99
     then
    0.99
     übrigens
    0.99
    Activations Density 0.093%

    No Known Activations