© 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. 10-GEMMASCOPE-RES-131K
    7. 39860
    Prev
    Next
    INDEX
    Explanations

    Rhodes or Rhode Island

    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
    
    -2.89
    
    -2.73
    鲣
    -2.67
    霂
    -2.66
    隄
    -2.56
    ?”
    -2.50
    立場
    -2.45
    偌
    -2.42
    ).
    -2.42
    !”
    -2.41
    POSITIVE LOGITS
    ’
    3.08
    2.84
    s
    2.72
    но
    2.67
    𖦹
    2.16
      
    2.14
    以及
    2.02
    鱨
    1.99
     trám
    1.97
     ajuste
    1.92
    Activations Density 0.005%
    No Known Activations