© 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. 22-GEMMASCOPE-RES-131K
    7. 66336
    Prev
    Next
    INDEX
    Explanations

    code execution context

    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_22/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
     ہے۔
    -1.06
    fläche
    -0.97
     وقد
    -0.95
    vamo
    -0.95
     télécharge
    -0.93
    Either
    -0.92
    should
    -0.90
    ărilor
    -0.90
     avaliações
    -0.89
    なので
    -0.88
    POSITIVE LOGITS
     then
    1.58
     thì
    1.50
     Then
    1.18
     puis
    1.16
     succeed
    1.13
     successful
    1.09
     satisfactory
    1.07
     successfully
    1.05
    Then
    1.03
    =[],
    1.02
    Activations Density 0.005%

    No Known Activations