© 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. 32568
    Prev
    Next
    INDEX
    Explanations

    transform change disguise form

    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
    underbrace
    -0.78
     aufgebaut
    -0.78
     lưu
    -0.74
    عد
    -0.73
    untamente
    -0.73
     hivyo
    -0.71
    ospels
    -0.70
    Bachelor
    -0.69
    فا
    -0.69
     Excavation
    -0.69
    POSITIVE LOGITS
     transformation
    4.41
     transform
    3.78
     transformations
    3.77
     transformed
    3.70
     transforming
    3.67
     transforms
    3.66
    transformation
    3.63
     Transformation
    3.56
    Transformation
    3.42
    transform
    3.39
    Activations Density 0.042%

    No Known Activations