© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59354
    Prev
    Next
    INDEX
    Explanations

    quiet, peaceful, 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
     dowol
    -0.84
    BoundingBox
    -0.81
    rada
    -0.77
    ̎
    -0.76
    ე
    -0.75
    tinya
    -0.74
    श्यक
    -0.74
    directory
    -0.74
    auml
    -0.73
     gimnas
    -0.73
    POSITIVE LOGITS
     quiet
    3.34
     peaceful
    2.70
    quiet
    2.69
     tranquility
    2.52
     peace
    2.44
     Quiet
    2.42
    Quiet
    2.41
     quieter
    2.27
     calm
    2.25
     tranquillity
    2.17
    Activations Density 0.030%

    No Known Activations