© 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. 2223
    Prev
    Next
    INDEX
    Explanations

    rest and recovery

    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
    utors
    -0.91
    warz
    -0.83
    {?>
    -0.82
    NV
    -0.81
     '*')
    -0.77
    ERÍA
    -0.76
    inado
    -0.75
    raeli
    -0.75
    rootScope
    -0.75
    xba
    -0.74
    POSITIVE LOGITS
     rest
    5.13
     resting
    4.72
     rested
    4.53
     rests
    4.19
    Rest
    3.94
     Rest
    3.89
    rest
    3.72
    休息
    3.67
     descansar
    3.47
    resting
    3.39
    Activations Density 0.071%

    No Known Activations