© 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. 54227
    Prev
    Next
    INDEX
    Explanations

    years, dates, 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_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
     recently
    -1.47
    recently
    -1.30
    recent
    -1.18
     недавно
    -1.01
    をはじめ
    -0.99
    ⌀
    -0.98
     currently
    -0.97
     opro
    -0.96
    already
    -0.94
    previously
    -0.94
    POSITIVE LOGITS
     später
    1.45
     later
    1.39
     damals
    1.38
     pozdě
    1.29
     döne
    1.24
     subsequent
    1.16
     vė
    1.16
     decades
    1.15
     ouders
    1.09
     damaligen
    1.09
    Activations Density 0.026%

    No Known Activations