© 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. 109506
    Prev
    Next
    INDEX
    Explanations

    smile and its context

    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
    beforeSend
    -0.93
    摟
    -0.91
     personalmente
    -0.85
    一下子
    -0.80
     применение
    -0.79
     tamamen
    -0.79
     позволяют
    -0.77
     необхідно
    -0.75
     juos
    -0.74
    没有任何
    -0.73
    POSITIVE LOGITS
     smile
    2.06
     Smile
    1.91
     smiles
    1.67
     ear
    1.53
    Smile
    1.49
     smiled
    1.47
    smile
    1.45
     улыб
    1.45
     grin
    1.36
     SMI
    1.32
    Activations Density 0.005%

    No Known Activations