© 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. 48538
    Prev
    Next
    INDEX
    Explanations

    Downton Abbey

    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
    طيع
    -0.82
     Developmental
    -0.75
     Otto
    -0.74
    //---
    -0.71
     madre
    -0.71
     Eck
    -0.69
    
    -0.69
    {_
    -0.69
     outlay
    -0.68
    Gdx
    -0.68
    POSITIVE LOGITS
     Crawley
    1.05
    Dow
    0.96
    Craw
    0.89
    arist
    0.88
     servants
    0.88
     Craw
    0.82
    dow
    0.82
     Dow
    0.81
     downstairs
    0.81
     ammon
    0.77
    Activations Density 0.015%

    No Known Activations