© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98809
    Prev
    Next
    INDEX
    Explanations

    lay and its common continuations

    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_34/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
    طع
    -0.86
     Because
    -0.84
    これが
    -0.81
    واع
    -0.79
     joo
    -0.77
    絆
    -0.77
    攣
    -0.77
     Making
    -0.76
     Excessive
    -0.76
     região
    -0.75
    POSITIVE LOGITS
    Lay
    1.84
     Lay
    1.66
     lay
    1.55
    lay
    1.42
     lays
    1.38
     layoffs
    1.34
     LAY
    1.27
    LAY
    1.18
     groundwork
    1.16
    wers
    1.07
    Activations Density 0.007%

    No Known Activations