© 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. 84745
    Prev
    Next
    INDEX
    Explanations

    putting or prioritizing something first

    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
     utilise
    -0.80
     reductase
    -0.74
     Jab
    -0.74
     utilising
    -0.73
     idő
    -0.72
    øst
    -0.71
    álise
    -0.70
    kirchen
    -0.70
    一方面
    -0.70
    藐
    -0.70
    POSITIVE LOGITS
     put
    2.48
     prioritize
    2.47
     priority
    2.39
     prioriti
    2.36
    Put
    2.14
     puts
    2.13
     putting
    2.08
     prioritise
    2.02
    priority
    1.99
     priorities
    1.99
    Activations Density 0.035%

    No Known Activations