© 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. 10-GEMMASCOPE-RES-131K
    7. 87161
    Prev
    Next
    INDEX
    Explanations

    section references

    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_10/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
     člán
    -1.80
     dalších
    -1.66
    itisation
    -1.64
     systému
    -1.64
    AGUE
    -1.59
     ;
    -1.55
     doprav
    -1.52
    
    -1.51
    Invoices
    -1.51
     οποία
    -1.48
    POSITIVE LOGITS
     of
    1.70
     /
    1.68
    ()
    1.63
     '';
    1.61
     birçok
    1.59
     =
    1.57
    re
    1.55
     `
    1.55
     tienen
    1.52
    的人都
    1.52
    Activations Density 0.016%

    No Known Activations