© 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. 103779
    Prev
    Next
    INDEX
    Explanations

    additional information following notes

    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
     जिसमें
    -0.94
    Argent
    -0.90
     ejemplo
    -0.90
    ļa
    -0.88
    しくは
    -0.88
    でしたが
    -0.88
     examples
    -0.87
     description
    -0.87
    atisch
    -0.86
     example
    -0.86
    POSITIVE LOGITS
     about
    1.80
     regarding
    1.66
     concerning
    1.33
     notes
    1.24
     remarks
    1.23
     acerca
    1.15
    Regarding
    1.09
     dotyczące
    1.08
     comments
    1.04
    remarks
    1.03
    Activations Density 0.038%

    No Known Activations