© 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. 34548
    Prev
    Next
    INDEX
    Explanations

    walking and stopping

    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
     lying
    -1.02
     лежа
    -0.92
    κος
    -0.91
     сидит
    -0.91
     sitter
    -0.88
     Lying
    -0.88
     asleep
    -0.88
     sitting
    -0.88
     crawled
    -0.88
     kneeling
    -0.86
    POSITIVE LOGITS
     stopping
    2.09
     stop
    2.05
     stopped
    2.02
     stops
    2.02
     walking
    1.83
    Stopping
    1.74
    stopping
    1.64
     Stopping
    1.62
     destination
    1.57
    stopped
    1.55
    Activations Density 0.026%

    No Known Activations