© 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. 36602
    Prev
    Next
    INDEX
    Explanations

    recent goals and assists

    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
     was
    -2.27
     damals
    -1.66
     была
    -1.54
     were
    -1.42
     damaligen
    -1.36
     took
    -1.34
     its
    -1.32
     did
    -1.30
     بود
    -1.29
     decades
    -1.28
    POSITIVE LOGITS
     currently
    2.33
     lately
    2.30
     recently
    2.16
     since
    1.91
     recent
    1.86
     senaste
    1.81
    recently
    1.79
    currently
    1.71
    recent
    1.70
     been
    1.67
    Activations Density 0.024%

    No Known Activations