© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78122
    Prev
    Next
    INDEX
    Explanations

    lists and tables

    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
    銷
    -0.80
     ruffled
    -0.79
     schrift
    -0.77
    irdre
    -0.77
    formats
    -0.73
     Sedan
    -0.73
     FORMAT
    -0.72
    crapers
    -0.72
    ده
    -0.71
    bán
    -0.70
    POSITIVE LOGITS
     images
    1.64
     pictures
    1.44
     table
    1.34
     tables
    1.33
     Images
    1.33
     imágenes
    1.26
     image
    1.23
    Images
    1.23
     equations
    1.20
     photos
    1.17
    Activations Density 0.086%

    No Known Activations