© 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. 1999
    Prev
    Next
    INDEX
    Explanations

    transformation and scaling

    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
     Treas
    -0.84
    šina
    -0.79
     kubwa
    -0.75
    culado
    -0.74
    评价
    -0.72
    APAN
    -0.72
     cults
    -0.72
     arvio
    -0.72
     toiminta
    -0.72
     فعالیت
    -0.71
    POSITIVE LOGITS
     transformation
    1.83
     change
    1.71
     transformations
    1.58
     Transformation
    1.52
    change
    1.50
     changement
    1.39
    Change
    1.38
    Transform
    1.36
    Transformation
    1.35
     cambio
    1.33
    Activations Density 0.055%

    No Known Activations