© 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. 83977
    Prev
    Next
    INDEX
    Explanations

    legal relief and remedies

    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
     arbitration
    -0.80
     enclosed
    -0.79
    memoized
    -0.78
     hydroxyl
    -0.76
    ił
    -0.75
    dentist
    -0.75
    接收
    -0.72
     Anzeige
    -0.71
     Enclosed
    -0.71
    razos
    -0.71
    POSITIVE LOGITS
     relief
    2.09
    relief
    1.85
     remedy
    1.73
     Relief
    1.64
    Relief
    1.54
     remedies
    1.35
     RELIEF
    1.28
     reliefs
    1.22
     orders
    1.17
     Remedy
    1.13
    Activations Density 0.022%

    No Known Activations