© 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. 28532
    Prev
    Next
    INDEX
    Explanations

    endings and stages

    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
    Immediately
    -1.10
     yder
    -1.05
     kuan
    -0.99
     ferie
    -0.93
     dage
    -0.93
     sofort
    -0.91
     proceeded
    -0.89
     milj
    -0.88
     egens
    -0.88
    soort
    -0.87
    POSITIVE LOGITS
     eventually
    1.67
     ending
    1.42
     uiteindelijk
    1.41
     culmin
    1.40
    eventually
    1.39
     irgendwann
    1.34
     finally
    1.34
    最後は
    1.34
     cuando
    1.31
     eventual
    1.27
    Activations Density 0.104%

    No Known Activations