© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102728
    Prev
    Next
    INDEX
    Explanations

    Inducing relaxation and calm

    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
    Gran
    -0.86
     levanta
    -0.78
    Clo
    -0.78
    Motiv
    -0.78
    sprü
    -0.76
    <0xED>
    -0.74
    dora
    -0.74
     alimentation
    -0.73
     Motiv
    -0.72
     memenuhi
    -0.72
    POSITIVE LOGITS
     relax
    2.25
     relaxing
    2.19
     relaxation
    2.14
    Relax
    2.08
    relax
    2.03
     Relax
    2.00
     relaxed
    1.91
     relaxes
    1.91
     Relaxation
    1.83
     рассла
    1.54
    Activations Density 0.024%

    No Known Activations