© 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. 50239
    Prev
    Next
    INDEX
    Explanations

    complain about something

    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
     beliefs
    -0.96
     zweifel
    -0.96
     approve
    -0.96
     impone
    -0.91
    何回
    -0.90
     問
    -0.88
     excited
    -0.88
     encouraging
    -0.87
    緊張
    -0.87
     Gemü
    -0.85
    POSITIVE LOGITS
     loudly
    1.65
     about
    1.62
     bitterly
    1.52
    loud
    1.51
     loudest
    1.48
     loud
    1.41
     voc
    1.29
     louder
    1.24
    Loud
    1.24
     LOU
    1.23
    Activations Density 0.015%

    No Known Activations