© 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. 76457
    Prev
    Next
    INDEX
    Explanations

    James, Jamestown, Odisha, USD

    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
     predstav
    -0.71
    💷
    -0.69
     bể
    -0.68
     Drainage
    -0.68
     estrella
    -0.68
    rip
    -0.67
     vinho
    -0.66
    
    -0.66
    botto
    -0.66
    もっと
    -0.66
    POSITIVE LOGITS
     James
    1.25
    James
    1.12
     JAMES
    1.09
    james
    1.04
     james
    1.03
    Deadly
    0.95
    JAMES
    0.95
     Krise
    0.89
     Jamestown
    0.88
     Odisha
    0.79
    Activations Density 0.002%

    No Known Activations