© 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. 34-GEMMASCOPE-RES-131K
    7. 109458
    Prev
    Next
    INDEX
    Explanations

    lying or laid down horizontally

    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
     sitting
    -1.74
     ngồi
    -1.47
     sits
    -1.45
     Sitting
    -1.42
    sitting
    -1.32
    Sitting
    -1.28
     standing
    -1.23
     sit
    -1.23
     Standing
    -1.18
    Standing
    -1.10
    POSITIVE LOGITS
     on
    1.59
     flat
    1.10
     lay
    0.97
     prone
    0.95
     flach
    0.88
     stretched
    0.87
     laid
    0.85
    LAY
    0.83
     Lie
    0.82
    flat
    0.82
    Activations Density 0.014%

    No Known Activations